Abstract: A system and method for patient health data prediction and analysis which utilizes an automated text mining tool to automatically format ingested electronic health record data to be added to a knowledge graph, which enriches the edges between nodes of the knowledge graph with fully interactive edge data, which can extract a subgraph of interest from the knowledge graph, and which analyzes the subgraph of interest to generate a set of variables that define the subgraph of interest. The system utilizes a knowledge graph and data analysis engine capabilities of the data platform to extract deeper insights based upon the enriched edge data.

Abstract: A method and system of training a natural language processing network are provided. A corpus of data is received and one or more input features selected therefrom by a generator network. The one or more selected input features from the generator network are received by a first predictor network and used to predict a first output label. A complement of the selected input features from the generator network are received by a second predictor network and used to predict a second output label.

Abstract: Provided is a method and processing unit for computer-implemented analysis of a classification model which is adapted to map, as a prediction, a number of input instances, each of them having a number n of features, into a number of probabilities of output classes, as a classification decision, according to a predetermined function, and which is adapted to determine a relevance value for each feature resulting in a saliency map. The disclosure includes the step of identifying an effect of each feature on the prediction of the instance by determining, for each feature, a relevance information representing a contextual information for all features of the instance omitting the considered feature. Then, the relevance value for each feature is determined. Finally, the plurality of relevance values for the features of the instance is evaluated to identify the effect of each feature on the prediction of the instance.

Abstract: A method for performing positron emission tomography (PET) image denoising using a dilated convolutional neural network system includes: obtaining, as an input to the dilated convolutional neural network system, a noisy image; performing image normalization to generate normalized image data corresponding to the noisy image; encoding the normalized image data using one or more convolutions in the dilated convolutional neural network, whereby a dilation rate is increased for each encoding convolution performed to generate encoded image data; decoding the encoded image data using one or more convolutions in the dilated convolutional neural network, whereby dilation rate is decreased for each decoding convolution performed to generate decoded image data; synthesizing the decoded image data to construct a denoised output image corresponding to the noisy image; and displaying the denoised output image on an image display device, the denoised output image having enhanced image quality compared to the noisy image.

Abstract: A method for lossy image or video encoding, transmission and decoding, the method comprising the steps of: receiving an input image at a first computer system; encoding the first input training image using a first trained neural network to produce a latent representation; performing a quantization process on the latent representation to produce a quantized latent; entropy encoding the quantized latent using a probability distribution, wherein the probability distribution is defined using a tensor network; transmitting the entropy encoded quantized latent to a second computer system; entropy decoding the entropy encoded quantized latent using the probability distribution to retrieve the quantized latent; and decoding the quantized latent using a second trained neural network to produce an output image, wherein the output image is an approximation of the input training image.

Abstract: A computer-implemented method for generating a description of a target skill set using domain specific language, a computer program product, and a system. Embodiments may comprise, on a processor, ingesting a data set related to the target skill from a data store, semantically analyzing the data set to generate a skill ontology, generating a hyperplane to separate one or more priority skills from among the plurality of related skills, generating a description for the target skill from the one or more priority skills, and presenting the generated description to a user. The skill ontology may include relationships between the target skill and a plurality of related skills.

Abstract: Systems, devices, and methods are provided for detecting anomalous events from categorical data using autoencoders. A system may receive a data set associated with actions requested within the computing environment, wherein the data set includes first categorical data indicative of anomalous activity in the computing environment. The system may train an autoencoder to reconstruct approximations of requests associated with the computing environment based on the received data set, wherein training the autoencoder includes using a beta divergence and a maximum mean discrepancy divergence. The trained system may receive a request to invoke an action within the computing environment, may generate a reconstruction of the request to invoke the action using the trained autoencoder, may determine a normalcy score based on a probability that the reconstruction of the request exists in the training data set, and, based on the calculated normalcy score, may determine whether requests indicate anomalous data.

Abstract: A processor of an image automatic classification server may perform a method for automatically classifying images. The method includes receiving partial or entire contents of a plurality of products from an online shopping website, classifying the received contents of the plurality of products into each of the products and storing the contents classified by each of the products, extracting a plurality of product images of one product among the plurality of products form the stored contents, and automatically classifying the extracted product images of the one product into a plurality of categories to generate information for the one product. The information for the one product comprises information that classifies the plurality of product images of the one product for each of a plurality of categories to provide the classified product images to be selectable.

Abstract: A method for lossy image or video encoding, transmission and decoding, the method comprising the steps of: receiving an input image at a first computer system; encoding the input image using a first trained neural network to produce a latent representation; identifying one or more regions of the input image associated with high visual sensitivity; encoding the one or more regions of the input image associated with high visual sensitivity using a second trained neural network to produce one or more region latent representations; performing a quantization process on the latent representation and the one or more region latent representations; transmitting the result of the quantization process to a second computer system; decoding the result of the quantization process to produce an output image, wherein the output image is an approximation of the input image.

Abstract: Disclosed is an artificial intelligence (AI) server. The AI server includes a communication unit configured to communicate with an AI device; and an AI unit configured to receive feature data from the AI device, wherein the received feature data is generated by the AI device by obtaining sensing data and compressing the sensing data while preserving a feature of the sensing data; and input the received feature data to a deep learning model to obtain second sensing data for use in a recognition model related to an AI function of the AI device.

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: According to various embodiments, a method for generating one or more optimal neural network architectures is disclosed. The method includes providing an initial seed neural network architecture and utilizing sequential phases to synthesize the neural network until a desired neural network architecture is reached. The phases include a gradient-based growth phase and a magnitude-based pruning phase.

Abstract: This invention predicts results for a media clip posted to a social media influencer channel by maintaining a database of results data for media clips where an influencer channel includes media clips that include unstructured data, and structured data, and then provide to a first machine learning model a first set of channel data, extracting a first set of features, predicting a value for the first target variable, providing to a second machine learning model a second set of channel data including a second selection of structured data, and the predicted value of the first target variable, extracting a second set of features, and predicting a value for the second target variable.

Abstract: Methods and systems for high-resolution image inpainting are disclosed. An original high-resolution image to be inpainted is obtained, as well as an inpainting mask indicating an inside-mask area to be inpainted. The original high-resolution image is down-sampled to obtain a low-resolution image to be inpainted. Using a trained inpainting generator, a low-resolution inpainted image and a set of attention scores are generated from the low-resolution image. The attention scores represent the similarity between inside-mask regions and outside-mask regions. A high-frequency residual image is computed from the original high-resolution image. An aggregated high-frequency residual image is generated using the attention scores, including high-frequency residual information for the inside-mask area. A high-resolution inpainted image is outputted by combining the aggregated high-frequency residual image and a low-frequency inpainted image generated from the low-resolution inpainted image.

Abstract: A system, method and non-transitory computer readable medium for editing images with verbal commands are described. Embodiments of the system, method and non-transitory computer readable medium may include an artificial neural network (ANN) comprising a word embedding component configured to convert text input into a set of word vectors, a feature encoder configured to create a combined feature vector for the text input based on the word vectors, a scoring layer configured to compute labeling scores based on the combined feature vectors, wherein the feature encoder, the scoring layer, or both are trained using multi-task learning with a loss function including a first loss value and an additional loss value based on mutual information, context-based prediction, or sentence-based prediction, and a command component configured to identify a set of image editing word labels based on the labeling scores.

Abstract: Implementations are directed to generating simulated training examples for training of a machine learning model, training the machine learning model based at least in part on the simulated training examples, and/or using the trained machine learning model in control of at least one real-world physical robot. Implementations are additionally or alternatively directed to performing one or more iterations of quantifying a “reality gap” for a robotic simulator and adapting parameter(s) for the robotic simulator based on the determined reality gap. The robotic simulator with the adapted parameter(s) can further be utilized to generate simulated training examples when the reality gap of one or more iterations satisfies one or more criteria.

Abstract: Provided herein is a system for occupiable space automation using neural networks that delivers scalable and more intelligent occupiable space automation that can continuously learn from user actions and experiences and adapt to specific needs of each individual occupiable space. The occupiable space automation control system is built based on brain inspired multi-layer neural network with plastic connectivity between neurons. The occupiable space automation control system is configured to (a) adaptively predict previously learned activity patterns and (b) alert about potentially harmful or undesired activity patterns of the plurality of periphery devices based on response events of the plurality of artificial neurons and coupling strengths of the plurality of synapses. The occupiable space automation control system is configured to automatically operate the at least one controller based on the predicted activity pattern and/or provide user alerts based on a detected harmful activity pattern.

Abstract: The present disclosure relates to systems, methods, and products for identifying candidate molecule. The system includes a non-transitory memory storing instructions; and a processor in communication with the non-transitory memory. The processor executes the instructions to cause the system to receive drug data; convert the drug data into at least one point in a latent space using a grammar variational auto-encoder (VAE) model; receive a query for the at least one candidate molecule; select one or more points in the latent space; and create a k-dimensional tree graph based on the query for the at least one candidate molecule and the selected one or more points; determine a plurality of paths according to an interpolation technique; receive preference data; determine an optimum path; determine at least one candidate point on the optimum path; and determine a drug molecular structure using an inverse of the grammar VAE model.

Abstract: According to an aspect of an embodiment, operations may include selecting, from a training dataset, a first data point as a seed data point. The operations may further include generating a population of data points by application of a genetic model on the seed data point. The population of data points may include the seed data point and a plurality of transformed data points of the seed data point. The operations may further include determining a best-fit data point in the generated population of data points based on application of a fitness function on the generated population of data points. The operations may further include executing a training operation on the DNN based on the determined best-fit data point. The operations may further include obtaining a trained DNN for the first data point based on the training operation on the DNN based on the determined best-fit data point.

Abstract: The method solves several problems to assist the investigation of human activities, by creating a human activities set of objects, by using an advanced mathematic computation algorithm and a time-based n-dimensional space-curves formula Fi algorithm, by using matrices calculus and tensors calculus, by incorporating artificial intelligence analysis in combination with logic and contextual analysis to create a time-based human activities universal processor. The method extracts time-based escalating risk and priority concepts, anomalous understanding and time-based ranking information, generating action to take, identifying present and predicting future object position, motion and behavior. When, this method is loaded as an application on an automotive and a machine, the method will be at home replacing a human.