Sas Institute Inc.

North Carolina State University

Sas Industries Inc.

Ravinder Devarajan

Jordan Riley Benson

Himesh G Patel

David James Caira

James Allen Cox

Saratendu Sethi

Lisa Hope Everdyke

Bradley Edward Morris

Kalpesh Padia

Pat Berryman

Christopher Kendrick Edwards

Christopher Graham Healey

Timothy Joel Erikson

Lawrence Edmund Lewis

Samuel Paul Leeman-Munk

Shaoliang Nie

Mustafa Kabul

Frank Lee Wimmer

Douglas R Dotson

Rajiv Ramarajan

Nascif A Abousalh-Neto

Gowtham Dinakaran

Joseph Oliver Hines, Jr

David Langton Clarke

Ernest C Pasour, Iii

Recurrent neural networks (RNNs) can be visualized. For example, a processor can receive vectors indicating values of nodes in a gate of a RNN. The values can result from processing data at the gate during a sequence of time steps. The processor can group the nodes into clusters by applying a clustering method to the values of the nodes. The processor can generate a first graphical element visually indicating how the respective values of the nodes in a cluster changed during the sequence of time steps. The processor can also determine a reference value based on multiple values for multiple nodes in the cluster, and generate a second graphical element visually representing how the respective values of the nodes in the cluster each relate to the reference value. The processor can cause a display to output a graphical user interface having the first graphical element and the second graphical element.

Interactive visualizations for a recurrent neural network

Convolutional neural networks can be visualized. For example, a graphical user interface (GUI) can include a matrix of symbols indicating feature-map values that represent a likelihood of a particular feature being present or absent in an input to a convolutional neural network. The GUI can also include a node-link diagram representing a feed forward neural network that forms part of the convolutional neural network. The node-link diagram can include a first row of symbols representing an input layer to the feed forward neural network, a second row of symbols representing a hidden layer of the feed forward neural network, and a third row of symbols representing an output layer of the feed forward neural network. Lines between the rows of symbols can represent connections between nodes in the input layer, the hidden layer, and the output layer of the feed forward neural network.

Visualizing convolutional neural networks

Interactive visualizations of a convolutional neural network are provided. For example, a graphical user interface (GUI) can include a matrix having symbols indicating feature-map values that represent likelihoods of particular features being present or absent at various locations in an input to a convolutional neural network. Each column in the matrix can have feature-map values generated by convolving the input to the convolutional neural network with a respective filter for identifying a particular feature in the input. The GUI can detect, via an input device, an interaction indicating that that the columns in the matrix are to be combined into a particular number of groups. Based on the interaction, the columns can be clustered into the particular number of groups using a clustering method. The matrix in the GUI can then be updated to visually represent each respective group of columns as a single column of symbols within the matrix.

Interactive visualizations of a convolutional neural network

Deep neural networks can be visualized. For example, first values for a first layer of nodes in a neural network, second values for a second layer of nodes in the neural network, and/or third values for connections between the first layer of nodes and the second layer of nodes can be received. A quilt graph can be output that includes (i) a first set of symbols having visual characteristics representative of the first values and representing the first layer of nodes along a first axis; (ii) a second set of symbols having visual characteristics representative of the second values and representing the second layer of nodes along a second axis; and/or (iii) a matrix of blocks between the first axis and the second axis having visual characteristics representative of the third values and representing the connections between the first layer of nodes and the second layer of nodes.

Visualizing deep neural networks

A method of rendering an overview axis is provided. A first indicator indicating a first graph element type to present in a canvas panel is received. First sample data is generated to render an instance of the first graph element type in the canvas panel. A second instance of the first graph element type is rendered in an overview axis using the generated first sample data. A second indicator indicating a second graph element type as a basis for presenting the overview axis is received, wherein the second graph element type is a different graph element type from the first graph element type. Second sample data is generated to render an instance of the second graph element type in the overview axis to replace the rendered second instance of the first graph element type.

Overview axis having a different graph element type

Training data for training a neural network usable for electronic sentiment analysis can be automatically constructed. For example, an electronic communication usable for training the neural network and including multiple characters can be received. A sentiment dictionary including multiple expressions mapped to multiple sentiment values representing different sentiments can be received. Each expression in the sentiment dictionary can be mapped to a corresponding sentiment value. An overall sentiment for the electronic communication can be determined using the sentiment dictionary. Training data usable for training the neural network can be automatically constructed based on the overall sentiment of the electronic communication. The neural network can be trained using the training data. A second electronic communication including an unknown sentiment can be received. At least one sentiment associated with the second electronic communication can be determined using the neural network.

Automatically constructing training sets for electronic sentiment analysis

A method of automatically sharing data between graph elements is provided. First sample data is generated to render an instance of a first graph element type in a first cell. An indicator is received that indicates selection of a second graph element type and dropping of an indicator of the second graph element type into the first cell. Second sample data is generated to render an instance of the second graph element type in the first cell overlaid with a second instance of the first graph element type in the first cell. A common axis is used for the second instance of the first graph element type and the instance of the second graph element type. Data points used for the common axis are automatically shared between the second instance of the first graph element type and the instance of the second graph element type.

Automatic data sharing between multiple graph elements

In a method of computing sample data to render a graph element, first sample data is computed to render a first graph element type. A second indicator is received that indicates a second graph element type to present overlaid with the first graph element type. Second sample data is computed to render the second graph element type. Third sample data is computed to render a second instance of the first graph element type. The second instance of the first graph element type is rendered overlaid with the second graph element type using the computed second and third sample data. A first number of points computed for the second sample data is the same as a second number of points computed for the third sample data. A common axis is used, and the first number of points is determined based on a data type of the common axis.

Sample data computation for rendering of graph elements

First sample data is generated to render an instance of a first graph element type with a first axis. Second sample data is generated to render an instance of a second graph element type with a second axis parallel to the first axis. Data points used for the first axis are different from data points used for the second axis. A first axis selector is presented in association with the first axis. An indicator is received that indicates selection of the presented first axis selector. After receipt of the indicator, a second indicator is received that indicates selection of a shared role between the first axis and the second axis. After receipt of the second indicator, the instance of the second graph element type is rendered with the first axis. Third data points used for the second axis automatically have the same value as first data points used for the first axis.

User adjustable data sharing between multiple graph elements

In a method of rendering a plurality of graph elements, first sample data is generated to render an instance of a first graph element type in a first cell of a canvas panel. An indicator is received that indicates a second graph element type to present in the first cell overlaid with the instance of the first graph element type. Second sample data is generated to render an instance of the second graph element type in the first cell overlaid with the instance of the first graph element type. An indicator is received that indicates selection of a fourth indicator of the instance of the second graph element type. An indicator is received that indicates dropping of the fourth indicator into a second cell. Third sample data is generated to render a second instance of the second graph element type in the second cell.

Drag and drop of graph elements

A method of proportional highlighting of data is provided. A graph presented on a display includes a first axis, a second axis, and a first value marker that indicates a value determined from data selected for presentation. The first axis includes a minimum value and a maximum value. The second axis includes a plurality of category values. An indicator identifying a subset of the data is received. A proportional value is determined for the first value marker based on the received indicator. A second value marker indicating the proportional value is presented on the graph overlaid on the first value marker when the determined proportional value is between the minimum value and the maximum value. A scale adjustment marker is presented on the graph without adjusting the first axis when the determined proportional value is not between the minimum value and the maximum value.

Growing community of inventors

Cary, NC, United States of America

Ravinder Devarajan