Abstract: A method and system for multiple-input multiple-output (MIMO) detector selection using a neural network is herein disclosed. According to one embodiment, a method includes generating a labelled dataset of features and detector labels, training a multi-layer perceptron (MLP) network using the generated labelled dataset, and selecting a detector class from a plurality of detector classes based on outputs of the trained MLP network.

Abstract: Embodiments disclosed herein include a method of training a DNN. A processor initializes an element of an A matrix. The element may include a resistive processing unit. A processor determines incremental weight updates by updating the element with activation values and error values from a weight matrix multiplied by a chopper value. A processor reads an update voltage from the element. A processor determines a chopper product by multiplying the update voltage by the chopper value. A processor directs storage of an element of a hidden matrix. The element of the hidden matrix may include a summation of continuous iterations of the chopper product. A processor updates a corresponding element of a weight matrix based on the element of the hidden matrix reaching a threshold state.

Abstract: A process for optimizing loss functions includes progressively building better sets of parameters for loss functions represented as multivariate Taylor expansions in accordance with an iterative process. The optimization process is built upon CMA-ES. At each generation (i.e., each CMA-ES iteration), a new set of candidate parameter vectors is sampled. These candidate parameter vectors are sampled from a multivariate Gaussian distribution representation that is modeled by the CMA-ES covariance matrix and the current mean vector. The candidates are then each evaluated by training a model (neural network) using the candidates and determining a fitness value for each candidate against a validation data set.

Abstract: Methods and systems for beam search decoding. One of the methods includes initializing beam data specifying a set of k candidate output sequences and a respective total score for each of the candidate output sequences; updating the beam data at each of a plurality of decoding steps, comprising, at each decoding step: generating a score distribution that comprises a respective score for each token in the vocabulary; identifying a plurality of expanded sequences; generating, for each expanded sequence, a respective backwards-looking score; generating, for each expanded sequence, a respective forward-looking score; computing, for each expanded sequence, a respective total score from the respective forward-looking score for the expanded sequence and the respective backwards-looking score for the expanded sequence; and updating the set of k candidate output sequences using the respective total scores for the expanded sequences.

Abstract: Systems and methods for firmware-based diagnostics in heterogenous computing platforms are described. In an illustrative, non-limiting embodiment, an Information Handling System (IHS) may include a heterogeneous computing platform having a plurality of devices and a memory coupled to the platform, where the memory includes firmware instructions that, upon execution by a respective device among the plurality of devices, enables the respective device to provide a corresponding firmware service, and wherein at least one of the plurality of devices operates as an orchestrator configured to: execute or instruct a selected device among the plurality of devices to execute an Artificial Intelligence (AI) model configured to determine whether to trigger a diagnostics process; and, in response to the determination, trigger the diagnostics process.

Abstract: A method including training, by one or more processors, a generative AI model using first operating data from building equipment and a plurality of first service reports indicating a plurality of first problems associated with the building equipment. The method may include predicting, by the one or more processors using the generative AI model, one or more future problems likely to occur with the building equipment based on second operating data from the building equipment. The method may include automatically initiating, by the one or more processors, one or more actions to prevent the one or more future problems from occurring or mitigate an effect of the one or more future problems.

Abstract: A method, computer system, and a computer program product for invariant risk minimization games is provided. The present invention may include defining a plurality of environment-specific classifiers corresponding to a plurality of environments. The present invention may also include constructing an ensemble classifier associated with the plurality of environment-specific classifiers. The present invention may further include initiating a game including a plurality of players corresponding to the plurality of environments. The present invention may also include calculating a nash equilibrium of the initiated game. The present invention may further include determining an ensemble predictor based on the calculated nash equilibrium. The present invention may include deploying the determined ensemble predictor associated with the calculated nash equilibrium to make predictions in a new environment.

Abstract: A method for generating an object includes: providing a dataset having object data and condition data; processing the object data to obtain latent object data and latent object-condition data; processing the condition data to obtain latent condition data and latent condition-object data; processing the latent object data and the latent object-condition data to obtain generated object data; processing the latent condition data and latent condition-object data to obtain generated condition data; comparing the latent object-condition data to the latent condition-object data to determine a difference; processing the latent object data and latent condition data and one of the latent object-condition data or latent condition-object data to obtain a discriminator value; and selecting a selected object based on the generated object data.

Abstract: Embodiments of the present disclosure relate to a tensor access operation circuit in a neural processor circuit. The neural processor circuit further includes a data processor circuit and at least one neural engine circuit. The tensor access operation circuit indirectly accesses at least a region of a source tensor in a system memory having a rank, and maps one or more source components of the source tensor into an input tensor having another rank. The data processor circuit stores an output version of the input tensor obtained from the tensor access operation circuit and sends the output version of the input tensor as multiple of units of input data to the at least one neural engine circuit. The at least one neural engine circuit performs at least convolution operations on the units of input data and at least one kernel to generate output data.

Abstract: Disclosed are a method, an apparatus, a device, and a medium for image recognition via wireless federated learning. The method for image recognition via wireless federated learning includes: obtaining an image to be recognized and an initial image recognition model; adjusting parameters for the initial image recognition model via a preset accelerated mobile federated learning algorithm according to a target momentum factor to obtain a target image recognition model; and recognizing the image to be recognized through the target image recognition model to obtain text information corresponding to the image to be recognized.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network used to select actions to be performed by an agent interacting with an environment. One of the systems includes (i) a plurality of actor computing units, in which each of the actor computing units is configured to maintain a respective replica of the action selection neural network and to perform a plurality of actor operations, and (ii) one or more learner computing units, in which each of the one or more learner computing units is configured to perform a plurality of learner operations.

Abstract: Methods, systems, and computer program products for factchecking artificial intelligence models using blockchain are provided herein. A computer-implemented method includes obtaining at least one artificial intelligence model and at least one set of data related to the at least one artificial intelligence model; determining a set of characteristics based at least in part on the at least one artificial intelligence model and the at least one set of data; selecting one of a plurality of networks based at least in part on a target deployment of the at least one artificial intelligence model to verify the set of characteristics; generating a report based at least in part on verifying the set of characteristics using the selected network, wherein the report establishes a threshold level of trust for the at least one artificial intelligence model; and storing the report on a blockchain.

Abstract: The present disclosure proposes the use of a dual discriminator network that comprises a temporal discriminator network for discriminating based on temporal features of a series of images and a spatial discriminator network for discriminating based on spatial features of individual images. The training methods described herein provide improvements in computational efficiency. This is achieved by applying the spatial discriminator network to a set of one or more images that have reduced temporal resolution and applying the temporal discriminator network to a set of images that have reduced spatial resolution. This allows each of the discriminator networks to be applied more efficiently in order to produce a discriminator score for use in training the generator, whilst maintaining accuracy of the discriminator network. In addition, this allows a generator network to be trained to more accurately generate sequences of images, through the use of the improved discriminator.

Abstract: Systems and methods for generating synthetic intercorrelated data are disclosed. For example, a system may include at least one memory storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include training a parent model by iteratively performing steps. The steps may include generating, using the parent model, first latent-space data and second latent-space data. The steps may include generating, using a first child model, first synthetic data based on the first latent-space data, and generating, using a second child model, second synthetic data based on the second latent-space data. The steps may include comparing the first synthetic data and second synthetic data to training data. The steps may include adjusting a parameter of the parent model based on the comparison or terminating training of the parent model based on the comparison.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes one or more pre-normalized layers or one or more regularization normalization layers.

Abstract: A computer-implemented method for reinforcement learning with Logical Neural Networks (LNNs) is provided including receiving a plurality of observation text sentences from a target environment, extracting one or more propositional logic values from the plurality of observation text sentences, finding a class for each propositional logic value by using external knowledge, converting each propositional logic value into a first-order logic by replacing a part in the propositional logic value with a variable word, the part indicating the class, selecting a LNN based on the class among LNNs prepared in advance for each class, each LNN receiving the one or more propositional logic values as a status input and outputting an action with a score indicating a degree of preference for taking the action, and performing a highest score action to the target environment to obtain a next state of the target environment and a reward for the highest score action.

Abstract: A method of determining a counterfeit fingerprint by a system for determining a counterfeit fingerprint that includes an internal light source and an external light source, comprising: extracting a first fingerprint area of a first fingerprint image obtained from a light signal of the internal light source when a target object's fingerprint comes in contact with a fingerprint contact surface of the system for determining a counterfeit fingerprint; extracting a second fingerprint area of a second fingerprint image obtained from a light signal of the external light source based on the first fingerprint area; and inputting the first fingerprint area and the second fingerprint area into a pre-trained neural network of the system for determining a counterfeit fingerprint to output a result of determining whether the fingerprint is counterfeit.

Abstract: An item recommendation system receives a set of recommendable items and a request to select, from the set of recommendable items, a contrast group. The item recommendation system selects a contrast group from the set of recommendable items by applying a image modification model to the set of recommendable items. The image modification model includes an item selection model configured to determine an unbiased conversion rate for each item of the set of recommendable items and select a recommended item from the set of recommendable items having a greatest unbiased conversion rate. The image modification model includes a contrast group selection model configured to select, for the recommended item, a contrast group comprising the recommended item and one or more contrast items. The item recommendation system transmits the contrast group responsive to the request.

Abstract: Embodiments are provided that include generating, by an inter-modal predictor, predicted second-mode information for a first text-based record based on first-mode information of the first text-based record. Embodiments also include generating a first value by evaluating a first loss function that is based on a first difference between the second-mode information of the first text-based record as predicted and as observed; updating the inter-modal predictor based on the first value; generating, by the updated inter-modal predictor, predicted second-mode information for a second text-based record in the database based on first-mode information of the second text-based record; generating a second value by evaluating a second loss function that is based on a second difference between the second-mode information of the second text-based record as predicted and as observed; and training an operational model based on the second value.

Abstract: A storage and inference method for a deep-learning neural network comprises steps: establishing dummy nodes in a first artificial neural network to form a second artificial neural network; storing model parameters of the second artificial neural network in a first storage area, and storing parameters of the dummy nodes in a second storage area; and in inference, respectively retrieving the model parameters of the second artificial neural network and the parameters of the dummy nodes from the first storage area and the second storage area simultaneously; deleting interconnections between the dummy nodes of the second artificial neural network or setting the interconnections between the dummy nodes of the second artificial neural network to 0 according to the parameters of the dummy nodes before inference. The present invention prevents ANN from be deciphered through respectively storing model parameters and parameters of the dummy nodes in different locations.

Abstract: The present disclosure a method of operating user equipment (UE) in a wireless communication system, the method comprising: identifying layer information that is applied to a neural polar code; generating, based on the identified layer information, transmission data by encoding data that is input into the neural polar code; and transmitting the transmission data to a base station, wherein, based on polar code transformation, the neural polar code generates the transmission data by performing encoding, based on the polar code transformation, from an initial layer of the data to a first layer according to the identified layer information and by performing encoding through a neural network-based autoencoder after the first layer until the transmission data is generated.

Abstract: The disclosure claims a method of stimulating a conditional quantum master equation in a quantum transport process by a recurrent neural network, comprising the following steps of: establishing a recurrent neural network which is a long short term memory network (LSTM), wherein the LSTM comprises TLSTM cells arranged in chronological order, and each LSTM cell has an input value xt and an output value ht, and there is a parameter (W, b) in the LSTM cell; replacing the input value xt with a shot noise spectrum S(?) of the current obtained according to the conditional quantum master equation; replacing the output value ht with a trace of density matrices in the conditional quantum master equation; and replacing the parameter (W, b) with a connection between density matrices in the conditional quantum master equation at imminent moments.

Abstract: An approach is disclosed herein a sequence generation ecosystem using machine learning. The approach disclosed herein is a new approach to sequence generation in the context of validation that relies on machine learning to explore and identify ways to achieve different states. In particular, the approach divides the valid operations into different respective actions and action sequences. These actions are selected by machine learning models as they are being trained using online inference reinforcement learning. This online inference also is likely to result in the discovery of new states. Each state that has been identified is then used as a target to train a respective machine learning model. As part of this process a representation of all the states and actions or sequences of actions executed to reach those states is created. This representation, the respective machine learning models, or a combination thereof can then be used to generate different test sequences.

Abstract: Computer systems and computer-implemented methods for modifying a machine learning network, such as a deep neural network, to introduce judgment to the network are disclosed. A “combining” node is added to the network, to thereby generate a modified network, where activation of the combining node is based, at least in part, on output from a subject node of the network. The computer system then trains the modified network by, for each training data item in a set of training data, performing forward and back propagation computations through the modified network, where the backward propagation computation through the modified network comprises computing estimated partial derivatives of an error function of an objective for the network, except that the combining node selectively blocks back-propagation of estimated partial derivatives to the subject node, even though activation of the combining node is based on the activation of the subject node.

Abstract: A method comprises transmitting a first client model to a first computing device and a second client model to a second computing device; determining (i) a first predictive score ratio for the first computing device, and (ii) a first predictive score ratio for the second computing device; determining the first computing device and the second computing device match; determining (i) a second predictive score ratio for the first computing device, and (ii) a second predictive score ratio for the second computing device; and detecting an anomaly in the first computing device responsive to (i) the determining the first computing device and the second computing device match, and (ii) determining the second predictive score ratio for the first computing device exceeds the second predictive score ratio for the second computing device by an amount above a difference threshold.

Abstract: Computer-implemented machines, systems and methods for providing insights about misalignment in a latent space of a machine learning model. A method includes initializing a second weight matrix of a second artificial neural network based on a first weight matrix from a first artificial neural network. The method further includes applying transfer learning between the first artificial neural network and the second artificial neural network. The method further includes comparing the first latent space with the second latent space. The method further includes determining, responsive to the comparing, a first score indicating alignment of the first latent space and the second latent space. The method further includes determining, and responsive to the first score satisfying a threshold, an appropriateness of the machine learning model.

Abstract: Techniques and apparatuses are described for machine-learning architectures for broadcast and multicast communications. A network entity processes broadcast or multicast communications using a deep neural network (DNN) to direct the one or more broadcast or multicast communications to a targeted group of user equipments (UEs) using the wireless communication system. The network entity receives feedback from at least one user equipment (UE) of the targeted group of UEs. The network entity determines a modification to the DNN based on the feedback. The network entity transmits an indication of the modification to the targeted group of UEs. The network entity updates the DNN with the modification to form a modified DNN. The network entity processes the broadcast or multicast communications using the modified DNN to direct the broadcast or multicast communications to the targeted group of UEs using the wireless communication system.

Abstract: The present invention relates to a method and a computer-readable medium for providing service information including a bill customized to a user, in which when company information and industry information are received from the user through a first interface, one or more higher-order keywords are derived based on the company information and the industry information, a plurality of information to which one or more lower-order keywords matching an initial logical relation for a specific higher-order keyword selected by the user are mapped are provided to the user through a second interface according to the initial logical relation between one or more lower-order keywords that are set to each of the one or more higher-order keywords, and the user changes the initial logical relation that is preset to the specific higher-order keyword through a third interface so as to additionally receive a plurality of information matching the changed logical relation.

Abstract: Methods and apparatuses that generate a simulation object for a physical system are described. The simulation object includes a trained computing structure to determine future output data of the physical system in real time. The computing structure is trained with a plurality of input units and one or more output units. The plurality of input units include regular input units to receive input data and output data of the physical system. The output units include one or more regular output units to predict a dynamic rate of change of the input data over a period of time. The input data and output data of the physical system are obtained for training the computing structure. The input data represent a dynamic input excitation to the physical system over the period of time. And the output data represents a dynamic output response of the physical system to the dynamic input excitation over the period of time.

Abstract: Techniques for performing BF16 FMA in response to an instruction are described. In some examples, an instruction has fields for an opcode, an identification of location of a packed data source/destination operand (a first source), an identification of a location of a second packed data source operand, an identification of a location of a third packed data source operand, and an identification of location of a packed data source/destination operand, wherein the opcode is to indicate operand ordering and that execution circuitry is to, per data element position, perform a BF16 value fused multiply-accumulate operation using the first, second, and third source operands and store a result in a corresponding data element position of the source/destination operand.

Abstract: Described is a system for performing a simulated vehicle control task based on adversarial decision analysis. Empirical game theoretic analyses are performed between an evolving and an adversary population of neural network strategies. Each empirical game theoretic analysis includes using a neuroevolution procedure to perform a fitness-based selection of a strategy in the evolving population that out-performs the adversary population. Using an empirical game theory procedure, the neuroevolution procedure is iteratively run and the selected strategy is added to the adversary population with each iteration, resulting in monotonic strategy improvement with each iteration. Following the empirical game theoretic analyses, a final strategy is selected for the evolving population and the adversary population using a tournament selection procedure. The final strategy is used to train a neural network which is used to perform a simulated vehicle control task.

Abstract: A mechanism is described for facilitating smart convolution in machine learning environments. An apparatus of embodiments, as described herein, includes one or more processors including one or more graphics processors, and detection and selection logic to detect and select input images having a plurality of geometric shapes associated with an object for which a neural network is to be trained. The apparatus further includes filter generation and storage logic (“filter logic”) to generate weights providing filters based on the plurality of geometric shapes, where the filter logic is further to sort the filters in filter groups based on common geometric shapes of the plurality of geographic shapes, and where the filter logic is further to store the filter groups in bins based on the common geometric shapes, wherein each bin corresponds to a geometric shape.

Abstract: Some embodiments provide a method that receives a specification of a neural network for execution by an integrated circuit. The integrated circuit includes a neural network inference circuit for executing the neural network to generate an output based on an input, an input processing circuit for providing the input to the neural network inference circuit, a microprocessor circuit for controlling the neural network inference circuit and the input processing circuit, and a unified memory accessible by the microprocessor circuit, the neural network inference circuit, and the input processing circuit. The method determines usage of the unified memory by the neural network inference circuit while executing the neural network. Based on the determined usage by the neural network inference circuit, the method allocates portions of the unified memory to the microprocessor circuit and input processing circuit.

Abstract: A network management system includes a non-transitory computer readable medium configured to store instructions thereon. The network management system further includes a processor connected to the non-transitory computer readable medium. The processor is configured to execute the instructions for receiving first log data from a first component in a network, wherein the first log data includes first log information; and parsing the first log data using a trained neural network to define parsed log data, wherein parsing the first log data includes organizing the first log information into a predefined sequence of information, and the parsed log data includes at least a signal source and a signal message. The processor is configured to execute the instructions for generating a unified model language (UML) diagram based on the parsed log data; and determining whether an error is present in the first component based on the UML diagram.

Abstract: Displaying visual indications of one or more files that are associated with a file being viewed via an augmented reality headset may be facilitated. In some embodiments, an image of a file being viewed by a user may be received. The system may determine whether a file is associated with a first error indicating an inconsistency between the file and one or more other files related to the file. Based on determining that the file is associated with the first error, the system may retrieve, based on one or more file identifiers corresponding to the one or more other files, one or more other files associated with the inconsistency. The system may then generate for display (i) a visual indicator indicating the first error and (ii) one or more visual indications of the one or more other files associated with the inconsistency.

Abstract: A method for processing a video includes receiving a video as an input at a first layer of an artificial neural network (ANN). A first frame of the video is processed to generate a first label. Thereafter, the artificial neural network is updated based on the first label. The updating is performed while concurrently processing a second frame of the video. In doing so, the temporal inconsistency between labels is reduced.

Abstract: Systems and methods for image captioning are described. One or more aspects of the systems and methods include generating a training caption for a training image using an image captioning network; encoding the training caption using a multi-modal encoder to obtain an encoded training caption; encoding the training image using the multi-modal encoder to obtain an encoded training image; computing a reward function based on the encoded training caption and the encoded training image; and updating parameters of the image captioning network based on the reward function.

Abstract: Embodiments described herein provide systems and methods for learning representation from unlabeled videos. Specifically, a method may comprise generating a set of strongly-augmented samples and a set of weakly-augmented samples from the unlabeled video samples; generating a set of predictive logits by inputting the set of strongly-augmented samples into a student model and a first teacher model; generating a set of artificial labels by inputting the set of weakly-augmented samples to a second teacher model that operates in parallel to the first teacher model, wherein the second teacher model shares one or more model parameters with the first teacher model; computing a loss objective based on the set of predictive logits and the set of artificial labels; updating student model parameters based on the loss objective via backpropagation; and updating the shared parameters for the first teacher model and the second teacher model based on the updated student model parameters.

Abstract: A response style component removal device capable of removing a response style that does not depend on content of a questionnaire is provided. The response style component removal device generates a probability of rating values for question items from raters who have rated questionnaires. Specifically, learning data for training the device include rating values for a plurality of question items from a plurality of raters who have rated a plurality of types of questionnaires. The device is configured to learn a rater parameter ?k that indicates a tendency of each rater, an item parameter ?k that indicates a tendency of each question item, and a response style parameter ? indicates a tendency of a response style, the rater parameter ?k, the item parameter ?k. The device is further configured to remove the response style parameter ? to generate a probability distribution of the rating value.

Abstract: A data analysis apparatus using a first neural network comprises: a setting unit configured to receive output data from the first input layer, set a weight of each layer in the first intermediate layer based on the output data and a second learning parameter, and output said weight to the first output layer; a weight processing unit included in the first output layer, the weight processing unit being configured to weight each output data with the weight of each layer of the first intermediate layer that was set by the setting unit; and a calculation unit included in the first output layer, the calculation unit being configured to calculate prediction data based on each output data that was weighted by the weight processing unit and a third learning parameter.

Abstract: Multiple artificial neural networks can be compiled as a single workload. A respective throughput for each of the artificial neural networks can be changed at runtime. The multiple artificial neural networks can be partially compiled individually and then later compiled just-in-time according to changing throughput demands for the artificial neural networks. The multiple artificial neural networks can be deployed on a deep learning accelerator hardware device.

Abstract: Embodiments of the disclosure provide a robot control method, apparatus and device, a computer storage medium and a computer program product and relate to the technical field of artificial intelligence. The method includes: acquiring environment interaction data and an actual target value, indicating a target that is actually reached by executing an action corresponding to action data in the environment interaction data; determining a return value after executing the action according to state data, action data and the actual target value at the first time of two adjacent times; updating a return value in the environment interaction data by using the return value after executing the action; training an agent corresponding to a robot control network by using the updated environment interaction data, and controlling the action of a target robot by using the trained agent.

Abstract: An online concierge system trains a user interaction model to predict a probability of a user performing an interaction after one or more content items are displayed to the user. This provides a measure of an effect of displaying content items to the user on the user performing one or more interactions. The user interaction model is trained from displaying content items to certain users of the online concierge system and withholding display of the content items to other users of the online concierge system. To train the user interaction model, the user interaction model is applied to labeled examples identifying a user and value based on interactions the user performed after one or more content items were displayed to the user and interactions the user performed when one or more content items were not used.

Abstract: The performance of a neural network (NN) and/or deep neural network (DNN) can limited by the number of operations being performed as well as management of data among the various memory components of the NN/DNN. A sparsity-inducing regularization optimization process is performed on a machine learning model to generate a compressed machine learning model. A machine learning model is trained using a first set of training data. A sparsity-inducing regularization optimization process is executed on the machine learning model. Based on the sparsity-inducing regularization optimization process, a compressed machine learning model is received. The compressed machine learning model is executed to generate one or more outputs.

Abstract: A computing system is disclosed that includes a processor and memory. The memory stores instructions that, when executed by the processor, cause the processor to perform several acts. The acts include receiving, by a generative model, input set forth by a user of a client computing device that is in network communication with the computing system. The acts also include generating, by the generative model, a query based upon the input set forth by the user; providing the query to a search engine. The acts further include receiving, by the generative model and from the search engine, content identified by the search engine based upon the query. The acts additionally include generating, by the generative model, an output based upon a prompt, where the prompt includes the content identified by the search engine based upon the query. The acts also include transmitting the output to the client computing device for presentment to the user.

Abstract: A hybrid personal watercraft combines features of pontoon boats and deck boats, in a cost-effective and versatile package. The watercraft includes port and starboard sponsons which combine a pair of outboard flotation cavities. A space below the deck and above the hull bottom creates at least one, and potentially up to three additional flotation cavities, which may also be used as storage areas accessible by an access door in the bow of the watercraft and/or a set of hatches in the deck. The watercraft may be efficiently produced assembled from polymer materials, such as thermoplastic polyolefin (TPO).

Abstract: A semiconductor device includes a first transistor including a first channel layer of a first conductivity type, a second transistor provided in parallel with the first transistor and including a second channel layer of a second conductivity type, and a third transistor stacked on the first and second transistors. The third transistor may include a gate insulating film including a ferroelectric material. The third transistor may include third channel layer and a gate electrode that are spaced apart from each other in a thickness direction with the gate insulating film therebetween.

Abstract: An electronic device according to an example embodiment includes a processor, and a memory operatively connected to the processor and including instructions executable by the processor, wherein when the instructions are executed, the processor is configured to collect an EEG signal measuring brain activity and an fNIRS signal measuring the brain activity, and output a result of determining a type of the brain activity from a trained neural network model using the EEG signal and the fNIRS signal, and the neural network model may be trained to, extract an EEG feature from the EEG signal, extract an fNIRS feature from the fNIRS signal, extract a fusion feature based on the EEG signal and the fNIRS signal, and output the result of determining the type of the brain activity based on the EEG feature and the fusion feature.

Abstract: A computing device includes one or more processors, a first random access memory (RAM) comprising magnetic random access memory (MRAM), a second random access memory of a type distinct from MRAM, and a non-transitory computer-readable storage medium storing instructions for execution by the one or more processors. The computing device receives first data on which to train an artificial neural network (ANN) and trains the ANN by, using the first RAM comprising the MRAM, performing a first set of training iterations to train the ANN using the first data, and, after performing the first set of training iterations, using the second RAM of the type distinct from MRAM, performing a second set of training iterations to train the ANN using the first data. The computing device stores values for the trained ANN. The trained ANN is configured to classify second data based on the stored values.

Abstract: Systems, devices, and methods related to a deep learning accelerator and memory are described. An integrated circuit may be configured with: a central processing unit, a deep learning accelerator configured to execute instructions with matrix operands; random access memory configured to store first instructions of an artificial neural network executable by the deep learning accelerator and second instructions of an application executable by the central processing unit; one or more connections among the random access memory, the deep learning accelerator and the central processing unit; and an input/output interface to an external peripheral bus. While the deep learning accelerator is executing the first instructions to convert sensor data according to the artificial neural network to inference results, the central processing unit may execute the application that uses inference results from the artificial neural network.