Abstract: A method is disclosed to dynamically design acceleration units of neural networks. The method comprises steps of generating plural circuit description files through a neural network model; reading a model weight of the neural network model to determine a model data format of the neural network model; selecting one circuit description file from the plural circuit description files according to the model data format, so that the chip is reconfigured according to the selected circuit description file to form an acceleration unit adapted to the model data format. The acceleration unit is suitable for running a data segmentation algorithm, which may accelerate the inference process of the neural network model. Through this method the chip may be dynamically reconfigured into an efficient acceleration unit for the different model data format, thereby speeding up the inference process of the neural network model.

Abstract: Systems and methods for wireless communication with devices equipped with multiple antenna panels are provided. A UE may transmit UE assistance information (UAI) to a wireless communication device associated with other network information such as rank indicator (RI). The UAI may include an indication of a quantity of antenna panels in use, a relative power consumption indicator, and/or a thermal overhead indicator. This information may be used by the wireless communication device to determine a network configuration which reduces the power consumption and/or thermal overhead of the UE.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to map workloads. An example apparatus includes a constraint definer to define performance characteristic targets of the neural network, an action determiner to apply a first resource configuration to candidate resources corresponding to the neural network, a reward determiner to calculate a results metric based on (a) resource performance metrics and (b) the performance characteristic targets, and a layer map generator to generate a resource mapping file, the mapping file including respective resource assignments for respective corresponding layers of the neural network, the resource assignments selected based on the results metric.

Abstract: Systems, methods, apparatuses, and computer-readable media. An analog router of a first supertile of a plurality of supertiles of a network on a chip (NoC) may receive a first analog output from a first compute-in-memory tile of a plurality of compute-in-memory tiles of the first supertile. The analog router may determine, based on a configuration of a neural network executing on the NoC, that a destination of the first analog output includes a second supertile of the plurality of supertiles. An analog-to-digital converter (ADC) of the analog router may convert the first analog output to a first digital output and transmit the first digital output to the second supertile via a communications bus of the NoC.

Abstract: A control system unit for a 3-dimensional (3D) object manufacturing system is disclosed herein that comprises one or more sensors and a controller. The one or more sensors are to sense 3D-objects manufactured in the manufacturing system in accordance with product specification data and to generate sensor signals representative for the sensed 3D-objects. The controller is to determine 3D-object characteristics of said sensed 3D-objects on the basis of said sensor data signals and to issue one or more corresponding control signals to control a system actuator unit so as to act on said sensed 3D-objects in accordance with their respective determined characteristics. The controller comprises a synthetic sensor data module to generate synthetic sensor data from product specification data of 3D-objects to be manufactured with the object manufacturing system, to therewith simulate sensor data for said 3D-objects to be sensed when manufactured.

Abstract: Systems and methods are disclosed for improving on-chip security, while minimizes the latency and cost of security techniques to improve system-level performance and power simultaneously. The framework uses machine learning algorithms, such as an artificial neural network (ANN), for runtime attack detection with higher accuracy. Further, a learning-based attack mitigation method using deep reinforcement learning is disclosed, where the method may be used to isolate the malicious components and to optimize network latency and energy-efficiency.

Abstract: Human drivers generally cannot plan a collision evasion maneuver in the brief interval before impact, other than simply slamming on the brakes and hoping for the best. Often the collision could have been avoided by swerving or other sequence of actions. Therefore, improved collision avoidance and mitigation procedures are disclosed, based on a well-trained artificial intelligence (AI) model that takes over the accelerator, brake, and steering in an emergency. With fast electronic reflexes and AI-based computational power, the AI model can find a more effective avoidance maneuver, or at least an action that would minimize the harm (for example, by swerving to miss the passenger compartment). The AI model can then implement the sequence instantly, without fear or hesitation. The result—fewer collisions and less fatality on our highways.

Abstract: A method comprises receiving an input signal for processing in one or more neurons of a neural network, wherein the neural network has zero bias neurons and includes a plurality of resistive processing unit (RPU) weights and each neuron has an activation function. The method also includes applying an arbitrary amplification factor to activation function outputs of the one or more neurons in the neural network, wherein the arbitrary amplification factor is based on a dynamic range of components in the neural network and compensates for conductance drift in values of the RPU weights. The method also includes performing a calculation with the neural network using the amplified activation function outputs of the one or more neurons.

Abstract: The present invention includes a CDR circuit including a phase detector, a neural network circuit, a controller and a clock signal generator is disclosed. The phase detector is configured to use a clock signal to sample an input signal to generate a plurality of phase detection results. The neural network circuit is coupled to the phase detector, and is configured to receive the plurality of phase detection results to determine information of a frequency difference between the clock signal and the input signal. The controller is configured to generate a control signal according to the information of the frequency difference between the clock signal and the input signal. The clock signal generator is configured to use the control signal to adjust a phase or frequency of the clock signal outputted to the phase detector.

Abstract: Systems, methods, and apparatuses for efficiently transmitting wireless communication signals are provided. An artificial neural network (ANN) is configured to take in an input data symbol sequence and generate a corresponding discrete-time Orthogonal Frequency Division Multiplexing (OFDM) sequence therefrom. The ANN combines multiple baseband signal-processing operations, one of which includes OFDM modulation. Training data tunes the ANN to provide the discrete-time OFDM signal with at least one of a low multiple input multiple output (MIMO) condition number, a predetermined number of eigenvalues above a threshold value, low peak-to-average-power ratio (PAPR), a low bit error probability, or a high bandwidth efficiency.

Abstract: An accelerator is disclosed. A tier storage may store data. A circuit may process the data to produce a processed data. The accelerator may load the data from a device using a cache-coherent interconnect protocol.

Abstract: Systems and computer-implemented methods for training a machine learnable model and for using the machine learned model for inference, both of which using only limited memory resources. During training and inference, the machine learnable model uses previous state information. A state memory is provided which efficiently stores this previous state information. Instead of storing each previous state individually and integrally, for each element of the internal state, a value is stored in the state memory which is indicative of a most recent occurrence of an element of the internal state of the machine learnable model holding or transitioning to a particular binary state value. The states of the machine learnable model are representable as binary values and when states infrequently hold or transition to a particular binary state value.

Abstract: Provided is a ticketing system adapted to retrieve a recommendation from a knowledge database in response to a received query, the ticketing system including a processor adapted to perform semantic similarity learning in textual description pairs by calculating similarity scores for similarities between the received query and tickets stored in the knowledge database of the ticketing system, wherein each textual description pair includes a textual description of the received query and a textual description of a ticket of a plurality of tickets stored in the knowledge database of the ticketing system, wherein the ticket having the maximum similarity score is identified and a solution of the identified ticket is output as the retrieved recommendation for the received query by the ticketing system.

Abstract: Systems and methods provide a first deployment criterion for deploying modified decision engines. A first existing decision engine is accessed, as well as a first modified decision engine that includes rule data generated by an artificial intelligence model based on the first existing decision engine. A first difference between a first output and a first modified output is determined, where the first output is generated by the first existing decision engine and the first modified output is generated by the first modified decision engine. A first selected decision engine is deployed to process subsequent data items to produce subsequent outputs, based on whether the first difference satisfies first deployment criterion. When metric generated based on the subsequent outputs satisfies a criterion modification condition, the artificial intelligence model is used to generate a second deployment criterion, wherein a second selected rule-based decision engine is deployed based on the second deployment criterion.

Abstract: A method of operating an apparatus using a control system that includes at least one neural network. The method includes receiving an input value captured by the apparatus, processing the input value using the at least one neural network of the control system implemented on first one or more solid-state chips, and obtaining an output from the at least one neural network resulting from processing the input value. The method may also include processing the output with another neural network implemented on solid-state chips to determine whether the output breaches a predetermined condition that is unchangeable after an initial installation onto the control system. The aforementioned another neural network is prevented from being retrained. The method may also include the step of using the output from the at least one neural network to control the apparatus unless the output breaches the predetermined condition. Similar corresponding apparatuses are described.

Abstract: Networks for distributing parameters and data to neural network compute cores. In various embodiments, a neural inference chip comprises a plurality of neural cores and at least one network interconnecting the plurality of neural cores. Each of the plurality of neural cores is adapted to apply a plurality of synaptic weights to a plurality of input activations to produce a plurality of output activations. The at least one network is adapted to simultaneously deliver synaptic weights and/or input activations to the plurality of neural cores.

Abstract: A method of predicting a brain atrophy condition for an individual using the individual's predicted age difference (PAD). The method comprises acquiring at least one brain image of the individual; processing the brain image to obtain at least one feature of the brain image; generating a PAD value of the individual based on the at least one feature of the image; and determining a brain atrophy condition of the individual based on the PAD value.

Abstract: A system and method of generating conversation topics using neural networks. The method includes providing, by a processing device, a plurality of conversations to a neural network to generate a plurality of clusters. The method includes selecting, for each cluster of the plurality of clusters, a topic and one or more keywords from one or more n-grams. The method includes evaluating, for each cluster of the plurality of clusters, the topic and the one or more keywords by searching historical conversations and current conversations to identify one or more conversations related to the cluster.

Abstract: The present specification discloses a calculation processing device which has a high processing rate with low cost. The calculation processing device according to the present specification is a calculation processing device including a fetch unit which reads, from a memory, data required for a calculation to perform processing of a neural network, and provides the data to a calculation unit. The fetch unit may comprise: multiple routers each having a data processing mapping table in which a scheme of processing input data is recorded according to a node identifier (ID) of the input data; and a fetch network controller which controls respective data processing mapping tables of the multiple routers.

Abstract: Systems and methods described herein relate to coordinated vehicle lane assignment. One embodiment receives from a locality manager, at a section manager that communicates with one or more connected vehicles in a section of a roadway, target lateral flows for two or more lanes of the roadway in the section of the roadway; converts the target lateral flows to a target number of connected vehicles N at the section manager; selects for lane change, at the section manager, a set of N connected vehicles whose ranked distances from a following vehicle in a target lane are greatest among the one or more connected vehicles, when a direction of lane change is uniform among the set of N connected vehicles; and transmits lane-change actions from the section manager to the set of N connected vehicles.

Abstract: Systems and methods described herein relate to traffic-flow regulation via centralized lateral flow control. One embodiment receives, at a locality manager that regulates traffic flow on a roadway via lateral flow control, aggregated macroscopic traffic state information from a section manager that communicates with one or more connected vehicles in a section of the roadway; processes the aggregated macroscopic traffic state information at the locality manager using a reinforcement-learning-based model to determine target lateral flows for two or more lanes of the roadway in the section of the roadway; and transmits the target lateral flows from the locality manager to the section manager, which converts the target lateral flows to lane-change actions and transmits the lane-change actions to the one or more connected vehicles.

Abstract: Spatial-temporal informative patterns for users and devices associated with data networks can be predicted or determined. An information management component (IMC) can analyze respective groups of items of data stored in respective formats in respective databases. Some items of data can comprise respective signal measurement data representative of respective signal measurements associated with respective devices associated with a communication network. Based on the analysis results, IMC can determine a spatial-temporal pattern(s) associated with the respective groups of items of data, wherein the spatial-temporal pattern(s) can relate to a subject of interest. The IMC can utilize artificial intelligence and/or machine learning algorithms and models to facilitate determining the spatial-temporal pattern(s). In response to a query relating to the subject of interest, the IMC can provide information relating to the subject of interest and responsive to the query based on the spatial-temporal pattern(s).

Abstract: It is possible to analyze what type of input/output mapping is mainly performed in the entire hidden layer of a neural network. A relationship analysis unit 30 calculates strength of a relationship of each combination of a dimension of the input data and a unit of the neural network and calculates strength of a relationship of each combination of the unit and a dimension of the output data. A role analysis unit 32 calculates a relationship between a prescribed number of types of roles and the unit and a relationship between the prescribed number of types of roles, the dimension of the input data, and the dimension of the output data on the basis of the strength of the relationship of each combination of the dimension of the input data and the unit of the neural network and the strength of the relationship of each combination of the unit and the dimension of the output data.

Abstract: Among other things, embodiments of the present disclosure help to overcome environment-specific dependency issues of conventional Wi-Fi-based sensing systems, thus allowing a neural network to make better proximity predictions in an unseen environment. Other embodiments may be described and claimed.

Abstract: Provided is a display panel which may include a pixel array including a plurality of pixels connected to scan lines and data lines, a photonic synapse block including a plurality of photonic synapse elements, and a neuron block including a plurality of neuron elements electrically connected to the plurality of photonic synapse elements.

Abstract: The present invention enables the structure of a neural network to be quantitatively analyzed. An analyzing unit calculates, for each of combinations of a dimension of input data and a cluster, a sum of squared errors between an output of each unit belonging to the cluster when a value of the dimension of the input data is replaced with an average value of the dimension of the input data included in learning data and an output of each unit belonging to the cluster for the input data before replacement as a relationship between the combinations, and calculates, for each of combinations of the cluster and a dimension of output data, a squared error between the value of the dimension of the output data when an output value of each unit belonging to the cluster is replaced with an average output value of each unit of the cluster when the input data included in the learning data was input and the value of the dimension of the output data before replacement as a relationship between the combinations.

Abstract: A computer-implemented method for training a classifier (??), including: training a pretext model (??) to learn a pretext task, so as to minimize a distance between an output of a source sample via the pretext model (??) and an output of a corresponding transformed sample via the pretext model (??), the transformed sample being a sample obtained by applying a transformation (T) to the source sample; S20) determining a neighborhood (NXi) of samples (Xi) of a dataset (SD) in the embedding space; S30) training the classifier (??) to predict respective estimated probabilities ??j(Xi), j=1 . . . C, for a sample (Xi) to belong to respective clusters (Cj), by using a second training criterion which tends to: maximize a likelihood for a sample and its neighbors (Xj) of its neighborhood (Nxi) to belong to the same cluster; and force the samples to be distributed over several clusters.

Abstract: Systems and methods for heterogenous hardware acceleration are disclosed. The systems and methods can include a neural network processing unit comprising compute tiles. Each of a first set of the compute tiles can include a first tensor array configured to support operations in a first number format. Each of a second set of the compute tiles can include a second tensor array configured to support operations in a second number format, the second number format supporting a greater range or a greater precision than the first number format, and a de-quantizer configured to convert data in the first number format to data in the second number format. The systems and methods can include neural network processing units, multi-chip hardware accelerators and distributed hardware accelerators including low-precision components for performing interference tasks and high-precision components for performing training tasks.

Abstract: The systems and methods provide an action recognition and analytics tool for use in manufacturing, health care services, shipping, retailing and other similar contexts. Machine learning action recognition can be utilized to determine cycles, processes, actions, sequences, objects and or the like in one or more sensor streams. The sensor streams can include, but are not limited to, one or more video sensor frames, thermal sensor frames, infrared sensor frames, and or three-dimensional depth frames. The analytics tool can provide for process validation, anomaly detection and in-process quality assurance.

Abstract: Systems, apparatuses and methods may provide for technology that aggregates contextual information from a first network layer in a neural network having a second network layer coupled to an output of the first network layer, wherein the context information is to be aggregated in real-time and after a training of the neural network, and wherein the context information is to include channel values. Additionally, the technology may conduct an importance classification of the aggregated context information and selectively exclude one or more channels in the first network layer from consideration by the second network layer based on the importance classification.

Abstract: The present disclosure relates to a method for representing an ordered group of symbols with a hypervector. The method comprises sequentially applying on at least part of the input hypervector associated with a current symbol a predefined number of circular shift operations associated with the current symbol, resulting in a shifted hypervector. A rotate operation may be applied on the shifted hypervector, resulting in an output hypervector. If the current symbol is not the last symbol of the ordered group of symbols the output hypervector may be provided as the input hypervector associated with a subsequent symbol of the current symbol; otherwise, the output hypervector of the last symbol of the ordered group of symbols may be provided as a hypervector that represents the ordered group of symbols.

Abstract: A delay spiking neural network (DSNN) may include a plurality of neurons arranged in a plurality of layers, with neurons spiking based on accumulation of delayed inputs. A first to spike neuron in an output layer may provide a result of the DSNN.

Abstract: In a neural network (NN) based wireless communication system, a BS determines, for an one-round latency T and an overall model size L of the NN model, i) Tu that makes {circumflex over (L)}*(Tu) larger than L and ii) Tl that makes {circumflex over (L)}*(Tl)<L; repeats determining {circumflex over (L)}*(Tm), {R*k,n}, {{circumflex over (L)}*k}, and {C*k,n} by using Tm=(Tu+Tl)/2 for k=1, K, and n=1, . . . N, while Tu is different from Tl; allocates NN model parameters to user equipments 1 to K based on {R*k,n}, {L*k}, and {C*k,n} determined based on Tm when Tu=Tl; and updates the NN model based on update results of the NN model parameters received from user equipments 1 to K.

Abstract: A program causes a computer to execute processing including: acquiring an endoscope image captured by an endoscope; inputting the acquired endoscope image into a plurality of learning models learned so as to output diagnosis support information regarding a lesion included in the endoscope image; acquiring a plurality of pieces of diagnosis support information output from each of the learning models; and outputting a plurality of pieces of the acquired diagnosis support information and information regarding each of the learning models in association with each other. Alternatively, the program causes the computer to execute the processing of inputting the acquired endoscope image into one learning model, executing a plurality of determination logics to acquire a plurality of pieces of output diagnosis support information, and outputting a plurality of pieces of the acquired diagnosis support information and information regarding each of the learning models in association with each other is executed.

Abstract: A processor-implemented neural network method includes: extracting, by a feature extractor of a neural network, a plurality of training feature vectors corresponding to a plurality of training class data of each of a plurality of classes including a first class and a second class; determining, by a feature sample generator of the neural network, an additional feature vector of the second class based on a mean vector and a variation vector of the plurality of training feature vectors of each of the first class and the second class; and training a class vector of the second class included in a classifier of the neural network based on the additional feature vector and the plurality of training feature vectors of the second class.

Abstract: An artificial neural network (ANN) apparatus can include processing component circuitry that receives linear inputs, and removes linearity from the one or more linear inputs based on an S-shaped saturating activation function that generates a continuous non-linear output. The neurons of the ANN comprise digital bit-wise components configured to transform the linear inputs into the continuous non-linear output.

Abstract: An image-based real-time intrusion detection method and a surveillance camera that use artificial intelligence are provided to sample a plurality of frames input at a first point in time, acquire a probability that at least one object corresponding to a type of a target object exists in an image of the respective sampled frames by using a first artificial neural network, adjust a sampling rate for a plurality of frames to be input at a second point in time after the first point in time according to processing time of each frame of the first artificial neural network required to acquire an existence probability of the at least one object, select each of the respective sampled frames as a frame of the target object according to a magnitude of the acquired probability, generate a movement trajectory of each object corresponding to the type of the target object from the frames selected as the frame of the target object, and acquire an intrusion occurrence probability from the generated movement trajectory by usin

Abstract: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure receive a span of text comprising an offensive span and a non-offensive span, generate a contextualized word embedding for each of a plurality of words of the span of text, generate a refined vector representation for each of the plurality of words based on the corresponding contextualized word embedding using a refinement network trained for offensive text recognition, generate label information for each of the plurality of words based on the corresponding refined vector representation, wherein the label information indicates whether each of the plurality of words includes offensive text, and transmit an indication of a location of the offensive span based on the label information.

Abstract: Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of accessing first transaction data stored in a transaction database, the first transaction data describing first transactions for first items from first users; determining, using the first transaction data, first micro-intents associated with the first transaction data; grouping the first micro-intents into clusters; labeling each cluster of the first micro-intents with a respective label; receiving second transaction data of a user, the second transaction data describing second transactions for second items for the user; determining, using the second transaction data, second micro-intents present in the second transactions; receiving current transaction data from a user interface of an electronic device of the user; determining, using the current transaction data, that the user is expressing a curre

Abstract: An apparatus, such as a stacked artificial neural network, can include a semiconductor at a first level. The semiconductor can include first circuitry. A memory can be at a second level. Second circuitry can be at a third level such that the memory is between the first circuitry and the second circuitry. The first circuitry can be configured propagate a first signal to the memory. The memory can be configured to propagate a second signal, based on data stored in the memory, to the second circuitry in response to the first signal. The second circuitry can be configured to generate a data signal based on the second signal.

Abstract: A system and a method for robot control based on a memristive crossbar array comprises a sensor group, an input sensing signal modulator, a neuromorphic circuit, an output control signal modulator, an output device, an external supervisor module and a training controller; the neuromorphic circuit performs robot control, and the main part thereof is a memristor crossbar array with a fully-connected neural network structure, wherein a differential amplifying circuit and a multiplexing switch in the neuromorphic circuit are connected to the memristor crossbar array, an input signal vector is multiplied by a weight matrix stored in the memristor crossbar array, and one or more channels of analog output signals are obtained through the differential amplifying circuit.

Abstract: The present invention relates to methods and systems for encoding and processing representations that include continuous structures using vector-symbolic representations. The system is comprised of a plurality of binding subsystems that implement a fractional binding operation, a plurality of unbinding subsystems that implement a fractional unbinding operation, and at least one input symbol representation that propagates activity through a binding subsystem and an unbinding subsystem to produce a high-dimensional vector representation of a continuous space.

Abstract: For reducing oscillations in a technical system plurality of different controller settings for the technical system is received. For a respective controller setting signal representing a time series of operational data of the technical system controlled by the respective controller setting is received, the signal is processed, whereby the processing includes a transformation into a frequency domain, and an entropy value of the processed signal is determined. Depending on the determined entropy values a controller setting from the plurality of controller settings is selected, and the selected controller setting is output for configuring the technical system.

Abstract: This disclosure provides systems, methods, and apparatus for determining whether an incident radio-frequency (RF) signal is from a known transmission source based on a match between a signature of the incident RF signal and at least one stored signature. One or more antennas can generate a plurality of electrical signals corresponding to a portion of a pulse of the incident RF signal. At least one of amplitude or phase values of a first electrical signal and phase coherent second electrical signal can be determined in the frequency domain. The signature of the incident RF signal based on at least one of amplitude or phase values of the first and the second electrical signals can be determined. This signature can be compared with stored signatures to determine whether the incident RF signal is from a known transmission source.

Abstract: Systems and methods for lifelong schema matching are described. The systems and methods include receiving data comprising a plurality of information categories, classifying each information category according to a schema comprising a plurality of classes, wherein the classification is performed by a neural network classifier trained based on a lifelong learning technique using a plurality of exemplar training sets, wherein each of the exemplar training sets includes a plurality of examples corresponding to one of the classes, and wherein the examples are selected based on a metric indicating how well each of the examples represents the corresponding class, and adding the data to a database based on the classification, wherein the database is organized according to the schema.

Abstract: A method for operating a multi-agent system including multiple robots. Each robot cyclically carries out the following: starting from an instantaneous system state, ascertaining possible options, the options defining actions via which a transition from an instantaneous system state to a subsequent system state may be achieved; for each possible option, ascertaining action costs for carrying out an action indicated by the option; carrying out an auction, the action cost values ascertained for each option being taken into account by each of the other robots; and executing an action that corresponds to one of the options as a function of all cost values ascertained or received for the option in question, the action costs for an option taking into account an empirical parameter that is a function of costs for past actions, which have already been carried out and which are associated with the option, of the multiple robots.

Abstract: An information processing apparatus (2000) acquires input data (10) and generates, by use of a neural network (30), condition data (50) that indicate one or more conditions satisfied by the input data (10). The information processing apparatus (2000) determines prediction data (20) by use of a value determined based on correct answer data (42) associated with example data (40) that satisfy at least a part of conditions indicated by the condition data (50).

Abstract: A method for selecting an AI solution for an automated robotic process including receiving at least one functional media including information indicative of brain activity by a human engaged in a task of interest, analyzing the functional media, identifying an activity level in at least one brain region, identifying a brain region parameter and an activity parameter; identifying an action parameter based in part on the brain region parameter or the activity parameter; and selecting a component of the AI solution in part on the brain region parameter, the activity parameter, or the action parameter.

Abstract: The network comprises at least one network layer in which a plurality of electronic oscillators, interconnected via programmable coupling elements storing respective network weights, generate oscillatory signals at time delays dependent on the input signal to propagate the input signal from an input to an output of that layer. The network is adapted to provide a network output signal dependent substantially linearly on phase of oscillatory signals in the last layer of the network. The method includes calculating a network error dependent on the output signal and a desired output for the training sample, and calculating updates for respective network weights by backpropagation of the error such that weight-updates for a network layer are dependent on a vector of time delays at the input to that layer and the calculated error at the output of that layer.

Abstract: Examples of biomimetic codecs and biomimetic coding techniques are described herein. Morphologically-adaptive coding networks can be developed in accordance with energy dissipation driven “heat” generated by application of training data. The morphologically-adaptive coding networks may be representative of common features expected in an input signal or data stream. Decoding may proceed using the morphologically-adaptive coding network. Morphologically-adaptive coding networks may be used as a cortex that can be shared for boosting multimedia data compression rates and/or increasing the encode-decode fidelity of information content while the features remain queryable in encoded form. Examples of the biomimetic codecs and biomimetic coding techniques provide a broad-based technology platform that can be used in context-IDed multimedia storage, pattern recognition, and high-performance computing/big data management, the hallmarks of web- and cloud-based systems.