Abstract: Causal explanations of outputs of a neural network can be learned from an attention layer in the neural network. The neural network may compute an output variable by processing a variable set including one or more input variables. An attention matrix may be computed by the attention layer in an abductive inference for which a new variable set including the input variables and the output variable is input into the neural network. Causal relationship between the variables in the new variable set may be determined based on the attention matrix and illustrated in a causal graph. A tree structure may be generated based on the causal graph. An input variable may be identified using the tree structure and determined to be the reason why the neural network computed the output variable. An explanation of the causal relation between the input variable and output variable can be generated and provided.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claimed.

Abstract: Various embodiments are generally directed to techniques for determining artificial neural network topologies, such as by utilizing probabilistic graphical models, for instance. Some embodiments are particularly related to determining neural network topologies by bootstrapping a graph, such as a probabilistic graphical model, into a multi-graphical model, or graphical model tree. Various embodiments may include logic to determine a collection of sample sets from a dataset. In various such embodiments, each sample set may be drawn randomly for the dataset with replacement between drawings. In some embodiments, logic may partition a graph into multiple subgraph sets based on each of the sample sets. In several embodiments, the multiple subgraph sets may be scored, such as with Bayesian statistics, and selected amongst as part of determining a topology for a neural network.

Abstract: A mechanism is described for facilitating learning and application of neural network topologies in machine learning at autonomous machines. A method of embodiments, as described herein, includes monitoring and detecting structure learning of neural networks relating to machine learning operations at a computing device having a processor, and generating a recursive generative model based on one or more topologies of one or more of the neural networks. The method may further include converting the generative model into a discriminative model.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer.

Abstract: A mechanism is described for facilitating learning and application of neural network topologies in machine learning at autonomous machines. A method of embodiments, as described herein, includes monitoring and detecting structure learning of neural networks relating to machine learning operations at a computing device having a processor, and generating a recursive generative model based on one or more topologies of one or more of the neural networks. The method may further include converting the generative model into a discriminative model.

Abstract: Methods and apparatus relating to techniques for incremental network quantization. In an example, an apparatus comprises logic, at least partially comprising hardware logic to determine a plurality of weights for a layer of a convolutional neural network (CNN) comprising a plurality of kernels; organize the plurality of weights into a plurality of clusters for the plurality of kernels; and apply a K-means compression algorithm to each of the plurality of clusters. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claimed.

Abstract: Methods and apparatus relating to techniques for incremental network quantization. In an example, an apparatus comprises logic, at least partially comprising hardware logic to determine a plurality of weights for a layer of a convolutional neural network (CNN) comprising a plurality of kernels; organize the plurality of weights into a plurality of clusters for the plurality of kernels; and apply a K-means compression algorithm to each of the plurality of clusters. Other embodiments are also disclosed and claimed.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claimed.

Abstract: A recursive method and apparatus produce a deep convolution neural network (CNN). The method iteratively processes an input directed acyclic graph (DAG) representing an initial CNN, a set of nodes, a set of exogenous nodes, and a resolution based on the CNN. An iteration for a node may include recursively performing the iteration upon each node in a descendant node set to create a descendant DAG, and upon each node in ancestor node sets to create ancestor DAGs, the ancestor node sets being a remainder of nodes in the temporary DAG after removing nodes of the descendent node set. The descendant and ancestor DAGs are merged, and a latent layer is created that includes a latent node for each ancestor node set. Each latent node is set to be a parent of sets of parentless nodes in a combined descendant DAG and ancestors DAGs before returning.

Abstract: Methods and apparatus relating to online activation compression with K-means are described. In one embodiment, logic (e.g., in a processor) compresses one or more activation functions for a convolutional network based on non-uniform quantization. The non-uniform quantization for each layer of the convolutional network is performed offline, and an activation function for a specific layer of the convolutional network is quantized during runtime. Other embodiments are also disclosed and claimed.

Abstract: Methods and apparatus relating to techniques for incremental network quantization. In an example, an apparatus comprises logic, at least partially comprising hardware logic to determine a plurality of weights for a layer of a convolutional neural network (CNN) comprising a plurality of kernels; organize the plurality of weights into a plurality of clusters for the plurality of kernels; and apply a K-means compression algorithm to each of the plurality of clusters. Other embodiments are also disclosed and claimed.

Abstract: Various embodiments are generally directed to techniques for determining artificial neural network topologies, such as by utilizing probabilistic graphical models, for instance. Some embodiments are particularly related to determining neural network topologies by bootstrapping a graph, such as a probabilistic graphical model, into a multi-graphical model, or graphical model tree. Various embodiments may include logic to determine a collection of sample sets from a dataset. In various such embodiments, each sample set may be drawn randomly for the dataset with replacement between drawings. In some embodiments, logic may partition a graph into multiple subgraph sets based on each of the sample sets. In several embodiments, the multiple subgraph sets may be scored, such as with Bayesian statistics, and selected amongst as part of determining a topology for a neural network.

Abstract: A recursive method and apparatus produce a deep convolution neural network (CNN). The method iteratively processes an input directed acyclic graph (DAG) representing an initial CNN, a set of nodes, a set of exogenous nodes, and a resolution based on the CNN. An iteration for a node may include recursively performing the iteration upon each node in a descendant node set to create a descendant DAG, and upon each node in ancestor node sets to create ancestor DAGs, the ancestor node sets being a remainder of nodes in the temporary DAG after removing nodes of the descendent node set. The descendant and ancestor DAGs are merged, and a latent layer is created that includes a latent node for each ancestor node set. Each latent node is set to be a parent of sets of parentless nodes in a combined descendant DAG and ancestors DAGs before returning.

Abstract: A mechanism is described for facilitating learning and application of neural network topologies in machine learning at autonomous machines. A method of embodiments, as described herein, includes monitoring and detecting structure learning of neural networks relating to machine learning operations at a computing device having a processor, and generating a recursive generative model based on one or more topologies of one or more of the neural networks. The method may further include converting the generative model into a discriminative model.

Abstract: In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claimed.

Abstract: The present invention extends to methods, systems, and computer program products for selecting candidate records for deduplication from a table. A table can be processed to compute an inverse index for each field of the table. A deduplication algorithm can traverse the inverse indices in accordance with a flexible user-defined policy to identify candidate records for deduplication. Both exact matches and approximate matches can be found.

Abstract: The present invention extends to methods, systems, and computer program products for selecting candidate records for deduplication from a table. A table can be processed to compute an inverse index for each field of the table. A deduplication algorithm can traverse the inverse indices in accordance with a flexible user-defined policy to identify candidate records for deduplication. Both exact matches and approximate matches can be found.

Abstract: The present invention extends to methods, systems, and computer program products for selecting candidate records for deduplication from a table. A table can be processed to compute an inverse index for each field of the table. A deduplication algorithm can traverse the inverse indices in accordance with a flexible user-defined policy to identify candidate records for deduplication. Both exact matches and approximate matches can be found.