公开(公告)号：US20160350652A1

公开(公告)日：2016-12-01

申请号：US14967619

申请日：2015-12-14

Applicant: North Carolina State University ,  SAS Institute Inc.

Inventor： Wookhee Min ,  Samuel Paul Leeman-Munk ,  Bradford Wayne Mott ,  James Curtis Lester, II ,  James Allen Cox

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06F17/24 ,  G06N3/0445 ,  G06N3/084 ,  H04L51/063

Abstract: A neural network can be used to determine edit operations for normalizing an electronic communication. For example, an electronic representation of multiple characters that form a noncanonical communication can be received. It can be determined that the noncanonical communication is mapped to at least two canonical terms in a database. A recurrent neural network can be used to determine one or more edit operations usable to convert the noncanonical communication into a normalized version of the noncanonical communication. In some examples, the one or more edit operations can include inserting a character into the noncanonical communication, deleting the character from the noncanonical communication, or replacing the character with another character in the noncanonical communication. The noncanonical communication can be transformed into the normalized version of the noncanonical communication by performing the one or more edit operations.

Abstract translation: 可以使用神经网络来确定用于规范化电子通信的编辑操作。 例如，可以接收形成非经典通信的多个字符的电子表示。 可以确定非数学通信被映射到数据库中的至少两个规范术语。 循环神经网络可以用于确定可用于将非经典通信转换为非规范通信的归一化版本的一个或多个编辑操作。 在一些示例中，一个或多个编辑操作可以包括将字符插入到非规范通信中，从非经典通信中删除字符，或者在非经典通信中用另一字符替换字符。 可以通过执行一个或多个编辑操作将非经典通信转换成非规范化通信的规范化版本。

公开(公告)号：US12277409B1

公开(公告)日：2025-04-15

申请号：US18895119

申请日：2024-09-24

Applicant: SAS INSTITUTE INC.

Inventor： Samuel Paul Leeman-Munk ,  Xiaozhuo Cheng ,  Xiaolong Li

IPC: G06F11/36 ,  G06F8/35 ,  G06F11/3604

Abstract: A system, method, and computer-program product includes identifying a plurality of code synthesis items for a target programming language, generating a code synthesis prompt based on a first sampling of the plurality of code synthesis items, synthesizing, via a large language model, a plurality of raw code segments using the code synthesis prompt, executing the plurality of raw code segments with a code interpreter associated with the target programming language, determining one or more valid code segments of the plurality of raw code segments that the code interpreter successfully executed, aggregating, via a second sampling, the one or more valid code segments into one or more validated code synthesis training samples, and training a code generation model using the one or more validated code synthesis training samples. User interfaces may be provided to allow target coding tasks to be specified via text or speech.

公开(公告)号：US11074412B1

公开(公告)日：2021-07-27

申请号：US17202413

申请日：2021-03-16

Applicant: SAS Institute Inc.

Inventor： Samuel Paul Leeman-Munk ,  James Allen Cox ,  David Blake Styles ,  Richard Welland Crowell

IPC: G06F40/30 ,  G06N20/00 ,  G06F40/284 ,  G06N3/04 ,  G06N3/08

Abstract: A system trains a classification model. Text windows are defined from tokens based on a window size. A network model including a transformer network is trained with the text windows to define classification information. A first accuracy value is computed. (A) The window size is reduced using a predefined reduction factor value. (B) Second text windows are defined based on the reduced window size. (C) Retrain the network model with the second text windows to define classification information. (D) A second accuracy value is computed. (E) An accuracy reduction value is computed from the second accuracy value relative to the first accuracy value. When the computed accuracy reduction value is ≥an accuracy reduction tolerance value, repeat (A)-(E) until the accuracy reduction value is

公开(公告)号：US10192001B2

公开(公告)日：2019-01-29

申请号：US15725026

申请日：2017-10-04

Applicant: SAS Institute Inc. ,  North Carolina State University

Inventor： Samuel Paul Leeman-Munk ,  Saratendu Sethi ,  Christopher Graham Healey ,  Shaoliang Nie ,  Kalpesh Padia ,  Ravinder Devarajan ,  David James Caira ,  Jordan Riley Benson ,  James Allen Cox ,  Lawrence E. Lewis ,  Mustafa Onur Kabul

IPC: G06N3/04 ,  G06F17/30

Abstract: 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.

公开(公告)号：US20180096078A1

公开(公告)日：2018-04-05

申请号：US15725026

申请日：2017-10-04

Applicant: SAS Institute Inc. ,  North Carolina State University

Inventor： Samuel Paul Leeman-Munk ,  Saratendu Sethi ,  Christopher Graham Healey ,  Shaoliang Nie ,  Kalpesh Padia ,  Ravinder Devarajan ,  David James Caira ,  Jordan Riley Benson ,  James Allen Cox ,  Lawrence E. Lewis ,  Mustafa Onur Kabul

IPC: G06F17/30 ,  G06N3/04

CPC classification number: G06F17/30994 ,  G06F17/30572 ,  G06F17/30958 ,  G06N3/04 ,  G06N3/105

Abstract: 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.

公开(公告)号：US20160350646A1

公开(公告)日：2016-12-01

申请号：US15175503

申请日：2016-06-07

Applicant: SAS Institute Inc.

Inventor： Samuel Paul Leeman-Munk ,  James Allen Cox

IPC: G06N3/04 ,  H04W4/00

CPC classification number: G06N3/0445 ,  G06N3/0454 ,  G06N3/0472

Abstract: Electronic communications can be normalized using a neural network. For example, a noncanonical communication that includes multiple terms can be received. The noncanonical communication can be preprocessed by (I) generating a vector including multiple characters from a term of the multiple terms; and (II) repeating a substring of the term in the vector such that a last character of the substring is positioned in a last position in the vector. The vector can be transmitted to a neural network configured to receive the vector and generate multiple probabilities based on the vector. A normalized version of the noncanonical communication can be determined using one or more of the multiple probabilities generated by the neural network. Whether the normalized version of the noncanonical communication should be outputted can also be determined using at least one of the multiple probabilities generated by the neural network.

Abstract translation: 电子通信可以使用神经网络进行归一化。 例如，可以接收包括多个术语的非经典通信。 非经典通信可以通过（I）从多个术语的术语生成包括多个字符的向量来预处理; 和（II）在向量中重复该项的子串，使得子串的最后一个字符位于向量中的最后位置。 向量可以被传送到被配置为接收向量并且基于向量生成多个概率的神经网络。 可以使用由神经网络生成的多个概率中的一个或多个来确定非规范通信的归一化版本。 还可以使用神经网络生成的多个概率中的至少一个来确定是否应该输出非规范通信的归一化版本。