Abstract: One embodiment of the present invention sets forth a technique for computer-implemented method for training a machine learning model includes appending context information to at least one portion of first data to generate second data, and performing one or more operations to train the machine learning model based on the second data to generate a trained machine learning model.

Abstract: One embodiment of the present invention sets forth a technique for computer-implemented method for training a machine learning model includes appending context information to at least one portion of first data to generate second data, and performing one or more operations to train the machine learning model based on the second data to generate a trained machine learning model.

Abstract: An artificial intelligence (AI) model includes one or more feature models coupled to one or more observer models in a hierarchical fashion. The feature models are configured to process an input to detect different features within that input. The observer models are configured to analyze the operation of the feature models during processing of the input to generate various types of observations. One type of observation includes a natural language expression that conveys how various architectural and/or functional characteristics of a given feature model influence the processing of the input to detect features, thereby exposing the underlying mechanisms via which the given feature model operates.

Abstract: One embodiment of a method for updating a simplified representation of a machine learning model includes receiving, from an edge device, data associated with execution of the simplified representation of the machine learning model on the edge device, performing one or more operations to re-train the machine learning model based on at least a portion of the data to generate a re-trained machine learning model, generating a simplified representation of the re-trained machine learning model, and transmitting, to the edge device, the simplified representation of the re-trained machine learning model for execution on the edge device.

Abstract: According to various embodiments, a direct air capture system includes: a wind turbine that includes at least one blade that includes one or more openings, wherein, in operation, first air flows across the at least one blade, causing the wind turbine to generate electrical energy, and causing the one or more openings to receive second air; a conduit that fluidly couples the one or more openings to a carbon dioxide (CO2) adsorption chamber that includes one or more amine-based CO2 adsorbers, wherein, in operation, the CO2 absorption chamber receives the second air via the one or more openings; and a carbon desorption apparatus that desorbs CO2 from the one or more amine-based CO2 adsorbers.

Abstract: One embodiment of the present invention sets forth a technique for performing inference operations associated with a trained machine learning model. The technique includes comparing a first input image with a plurality of image representations that are associated with a plurality of output classes predicted by the trained machine learning model. The technique also includes determining that the first input image does not match any image representation included in the plurality of image representations and subsequently determining that the first input image does match a first alternative representation that is associated with a first output class included in the plurality of output classes. The technique further includes generating a first prediction that indicates that the first input image is a member of the first output class.

Abstract: One embodiment of the present invention sets forth a technique for simplifying a trained machine learning model. The technique includes determining a first set of images associated with a first output class predicted by the trained machine learning model. The technique also includes generating a first aggregated representation of the first set of images, wherein the first aggregated representation includes a first plurality of representative pixel values for a plurality of pixel locations included in the first set of images. The technique further includes generating a simplified representation of the trained machine learning model that includes a first mapping of the first aggregated representation to the first output class, wherein the first mapping indicates that the trained machine learning model predicts the first output class for one or more input images.

Abstract: One embodiment of the present invention sets forth a technique for simplifying a trained machine learning model. The technique includes determining a first set of images associated with a first output class predicted by the trained machine learning model. The technique also includes generating a first logical representation of the first set of images, wherein the first logical representation includes one or more conjunctions of a first set of pixel values included in a first image and a disjunction of the first set of pixel values and a second set of pixel values included in a second image. The technique further includes generating a simplified representation of the trained machine learning model that includes a first mapping of the first logical representation to the first output class, wherein the first mapping indicates that the trained machine learning model predicts the first output class for one or more input images.

Abstract: As described, an artificial intelligence (AI) design application exposes various tools to a user for generating, analyzing, evaluating, and describing neural networks. The AI design application includes a network generator that generates and/or updates program code that defines a neural network based on user interactions with a graphical depiction of the network architecture. The AI design application also includes a network analyzer that analyzes the behavior of the neural network at the layer level, neuron level, and weight level in response to test inputs. The AI design application further includes a network evaluator that performs a comprehensive evaluation of the neural network across a range of sample of training data. Finally, the AI design application includes a network descriptor that articulates the behavior of the neural network in natural language and constrains that behavior according to a set of rules.

Abstract: As described, an artificial intelligence (AI) design application exposes various tools to a user for generating, analyzing, evaluating, and describing neural networks. The AI design application includes a network generator that generates and/or updates program code that defines a neural network based on user interactions with a graphical depiction of the network architecture. The AI design application also includes a network analyzer that analyzes the behavior of the neural network at the layer level, neuron level, and weight level in response to test inputs. The AI design application further includes a network evaluator that performs a comprehensive evaluation of the neural network across a range of sample of training data. Finally, the AI design application includes a network descriptor that articulates the behavior of the neural network in natural language and constrains that behavior according to a set of rules.

Abstract: As described, an artificial intelligence (AI) design application exposes various tools to a user for generating, analyzing, evaluating, and describing neural networks. The AI design application includes a network generator that generates and/or updates program code that defines a neural network based on user interactions with a graphical depiction of the network architecture. The AI design application also includes a network analyzer that analyzes the behavior of the neural network at the layer level, neuron level, and weight level in response to test inputs. The AI design application further includes a network evaluator that performs a comprehensive evaluation of the neural network across a range of sample of training data. Finally, the AI design application includes a network descriptor that articulates the behavior of the neural network in natural language and constrains that behavior according to a set of rules.

Abstract: An artificial intelligence (AI) design application that exposes various tools to a user for generating, analyzing, evaluating, and describing neural networks. The AI design application includes a network generator that generates and/or updates program code that defines a neural network based on user interactions with a graphical depiction of the network architecture. The network generator enables a developer to define the neural network architecture using a pipeline of mathematical expressions that can be directly compiled without the need of a complex software stack. The compilation process allows for the variables to be learned during the training process to be left unassigned when the neural network is instantiated. In particular, the compiler identifies such unassigned variables as variables having values that will be determined during the training process.

Abstract: One embodiment of the present invention sets forth a technique for quantizing a machine learning model. The technique includes selecting a default quantized version of the machine learning model based on a plurality of performance metrics for a plurality of quantized versions of the machine learning model. The technique also includes determining that a first output generated by the default quantized version based on a first set of feature values does not match a second output associated with the first set of feature values. The technique further includes storing a first mapping of one or more first feature values included in the first set of feature values to a first quantized version of the machine learning model in a lookup table representing the machine learning model, wherein the first quantized version is associated with a higher quantization resolution than the default quantized version.

Abstract: One embodiment of the present invention sets forth a technique for quantizing a machine learning model. The technique includes generating a first set of quantized feature values based on a first set of feature values inputted into the machine learning model and a first set of quantization levels. The technique also includes determining that a first output generated by the machine learning model based on the first set of quantized feature values does not match a second output associated with the first set of feature values. The technique further includes generating a second set of quantized feature values based on the first set of feature values and a second set of quantization levels that is associated with a higher quantization resolution than the first set of quantization levels, and storing a first mapping of the second set of quantized feature values to the first output in a lookup table.

Abstract: One embodiment of the present invention sets forth a technique for executing one or more services in a technology stack. The technique includes deploying a first set of containers within an environment, wherein each container included in the first set of containers includes a first service that implements a first interface and a first shim that implements a second interface. The technique also includes transmitting a first request associated with the second interface to a first container included in the first set of containers, wherein the first request is processed by an instance of the first shim and an instance of the first service executing within the first container.

Abstract: One embodiment of the present invention sets forth a technique for processing requests associated with one or more services. The technique includes deploying a first container within an environment, wherein the first container includes a first service that implements a first interface and a first shim that implements a second interface. The technique also includes receiving, at the first shim, a first request associated with the second interface. The technique further includes converting the first request into a second request associated with the first interface, and transmitting the second request over the first interface to the first service, wherein the second request is processed by the first service.

Abstract: Various embodiments set forth systems and techniques for augmenting neural networks. The techniques include causing one or more neural networks to generate first output based on a first input; identifying one or more rules associated with the first input; processing the first output based on the one or more rules to generate a second output; and transmitting the second output, instead of the first output, as a result of processing the first input.

Abstract: Various embodiments set forth systems and techniques for generating domain-specific question answering models. The techniques include receiving a set of input text corresponding to a particular domain; generating, based on the set of input text, a question-answer dataset corresponding to the particular domain, the question-answer dataset comprising a plurality of question-answer pairs; and causing one or more machine learning algorithms to be applied to the question-answer dataset to generate a question answering model associated with the particular domain.

Abstract: Various embodiments set forth systems and techniques for adaptive visualization of a quantized neural network. The techniques include generating one or more network visualizations of a neural network; determining, based on the one or more network visualizations, one or more quantization schemes associated with the neural network; and re-training the neural network or approximating the neural network, based on adjusting one or more quantization coefficients associated with the one or more quantization schemes.

Abstract: Various embodiments set forth systems and techniques for adaptive generation and visualization of a quantized neural network. The techniques include extracting, based on one or more input features and one or more non-quantized network parameters, one or more attributes; calculating, based on the one or more attributes, one or more quantization coefficients; generating, based on the one or more quantization coefficients, one or more quantized input features; and generating, based on the one or more quantized input features and one or more quantization techniques, a neural network.