公开(公告)号：US11651578B2

公开(公告)日：2023-05-16

申请号：US16329368

申请日：2017-01-11

Applicant: IFLYTEK CO., LTD.

Inventor： Jia Pan ,  Shiliang Zhang ,  Shifu Xiong ,  Si Wei ,  Guoping Hu

IPC: G06F12/00 ,  G06N3/08 ,  G06N3/049 ,  G06N99/00 ,  G10L15/06

CPC classification number: G06N3/08 ,  G06N3/049 ,  G06N99/00 ,  G10L15/06

Abstract: A method and a system for end-to-end modeling are provided. The method includes: determining a topological structure of a target-based end-to-end model, where the topological structure includes an input layer, an encoding layer, an code enhancement layer, a filtering layer, a decoding layer and an output layer; the code enhancement layer adds information of a target unit to a feature sequence outputted by the encoding layer, the filtering layer filters a feature sequence added with the information of the target unit; collecting multiple pieces of training data; and training parameters of the target-based end-to-end model by using the multiple pieces of the training data.

公开(公告)号：US11651163B2

公开(公告)日：2023-05-16

申请号：US16935784

申请日：2020-07-22

Applicant: Capital One Services, LLC

Inventor： Oluwatobi Olabiyi ,  Erik T. Mueller ,  Rui Zhang ,  Zachary Kulis ,  Varun Singh

IPC: G06F40/56 ,  G06F40/35 ,  G06N3/04 ,  G10L15/22 ,  G10L15/06 ,  G10L15/16 ,  G06N20/00 ,  G06K9/62 ,  G06F40/284 ,  G06F40/30 ,  G06N3/049 ,  G06F18/21 ,  G06F18/214

CPC classification number: G06F40/30 ,  G06F18/217 ,  G06F18/2148 ,  G06F40/284 ,  G06F40/35 ,  G06F40/56 ,  G06N3/049 ,  G06N20/00 ,  G10L15/063 ,  G10L15/16 ,  G10L15/22 ,  G10L2015/0631 ,  G10L2015/228

Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in particular tasks, such as turn-based dialogues. Machine classifiers may be used to help users to perform tasks indicated by the user. When a user utterance is received, natural language processing techniques may be used to understand the user's intent. Templates may be determined based on the user's intent in the generation of responses to solicit information from the user. A variety of persona attributes may be determined for a user. The persona attributes may be determined based on the user's utterances and/or provided as metadata included with the user's utterances. A response persona may be used to generate responses to the user's utterances such that the generated responses match a tone appropriate to the task. A response persona may be used to generate templates to solicit additional information and/or generate responses appropriate to the task.

公开(公告)号：US11645501B2

公开(公告)日：2023-05-09

申请号：US15908459

申请日：2018-02-28

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Arnon Amir ,  David Berg ,  Pallab Datta ,  Jeffrey A. Kusnitz ,  Hartmut Penner

IPC: G06N3/04 ,  G06N3/049 ,  G06N3/063 ,  G06N3/045 ,  G06N3/065 ,  G06N20/00

CPC classification number: G06N3/049 ,  G06N3/045 ,  G06N3/063 ,  G06N3/065 ,  G06N20/00

Abstract: Systems for distributed, event-based computation are provided. In various embodiments, the systems include a plurality of neurosynaptic processors and a network interconnecting the plurality of neurosynaptic processors. Each neurosynaptic processor includes a clock uncoupled from the clock of each other neurosynaptic processor. Each neurosynaptic processor is adapted to receive an input stream, the input stream comprising a plurality of inputs and a clock value associated with each of the plurality of inputs. Each neurosynaptic processor is adapted to compute, for each clock value, an output based on the inputs associated with that clock value. Each neurosynaptic processor is adapted to send to another of the plurality of neurosynaptic processors, via the network, the output and an associated clock value.

公开(公告)号：US11640681B2

公开(公告)日：2023-05-02

申请号：US17011651

申请日：2020-09-03

Applicant: CORNELL UNIVERSITY

Inventor： Sheila Nirenberg ,  Iliya Bomash

IPC: G06V10/44 ,  H04N19/62 ,  H04N19/85 ,  H04N19/60 ,  G06T7/00 ,  G06T9/00 ,  G06N3/04 ,  G06N3/049

Abstract: A method is disclosed including: receiving raw image data corresponding to a series of raw images; processing the raw image data with an encoder to generate encoded data, where the encoder is characterized by an input/output transformation that substantially mimics the input/output transformation of one or more retinal cells of a vertebrate retina; and applying a first machine vision algorithm to data generated based at least in part on the encoded data.

公开(公告)号：US11640520B2

公开(公告)日：2023-05-02

申请号：US17405967

申请日：2021-08-18

Applicant: NEURAVILLE, LLC

Inventor： Mohammad Nadji-Tehrani

IPC: G06F17/00 ,  G06N3/045 ,  B25J9/16 ,  G06N3/08 ,  G06N3/049

Abstract: A method for automatically generating a neural network architecture includes: loading a first computer-readable representation of a first neural network architecture including first genes representing parameters of the first neural network architecture; generating a first neural network including neurons in accordance with the first genes; deploying the first neural network in a robotic controller; training the first neural network by supplying inputs to an input processing unit connected to the first neural network and receiving outputs from an output processing unit connected to the first neural network, the training including updating synaptic weights of connections between the neurons based on responses to the inputs supplied to the input processing unit; evaluating a performance of the first neural network architecture; and generating, by the computer system, an updated computer-readable representation of an updated neural network architecture based on the evaluation of the performance the first neural network.

公开(公告)号：US11636347B2

公开(公告)日：2023-04-25

申请号：US16749252

申请日：2020-01-22

Applicant: DeepMind Technologies Limited

Inventor： Hanjun Dai ,  Yujia Li ,  Chenglong Wang ,  Rishabh Singh ,  Po-Sen Huang ,  Pushmeet Kohli

IPC: G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06N3/088 ,  G06N3/049

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a method comprises: obtaining a graph of nodes and edges that represents an interaction history of the agent with the environment; generating an encoded representation of the graph representing the interaction history of the agent with the environment; processing an input based on the encoded representation of the graph using an action selection neural network, in accordance with current values of action selection neural network parameters, to generate an action selection output; and selecting an action from a plurality of possible actions to be performed by the agent using the action selection output generated by the action selection neural network.

公开(公告)号：US11636318B2

公开(公告)日：2023-04-25

申请号：US16647814

申请日：2017-12-15

Applicant: INTEL CORPORATION

Inventor： Arnab Paul ,  Narayan Srinivasa

IPC: G06N3/04 ,  G06N3/049

Abstract: Techniques and mechanisms for servicing a search query using a spiking neural network. In an embodiment, a spiking neural network receives an indication of a first context of the search query, wherein a set of nodes of the spiking neural network each correspond to a respective entry of a repository. One or more nodes of the set of nodes are each excited to provide a respective cyclical response based on the first context, wherein a first cyclical response is by a first node. Due at least in part to a coupling of the excited nodes, a perturbance signal, based on a second context of the search query, results in a change of the first resonance response relative to one or more other resonance responses. In another embodiment, data corresponding to the first node is selected, based on the change, as an at least partial result of the search query.

公开(公告)号：US20230087722A1

公开(公告)日：2023-03-23

申请号：US17991161

申请日：2022-11-21

Applicant: NEUROCEAN TECHNOLOGIES INC.

Inventor： Hualong REN

IPC: G06N3/063 ,  G06N3/049 ,  G06N3/092

Abstract: A kind of neural network is provided which has memory and information abstract functions. This kind of brain neural network borrows the working principle of biological brain hippocampus and its surrounding brain regions, including the memory module can form the episodic memory. It allows the intelligent agent to efficiently identify objects and conduct space navigation, reasoning and independent decision making. It can quickly remember the characteristics of each object and carry out abstraction and meta-learning, has strong generalization ability, and can achieve the lifelong learning. It uses the synaptic plasticity process to adjust the weight, avoids partial differential operation, and has lower computational overhead than the traditional deep learning method, providing a basis for the design and application of neuromorphic chip.

公开(公告)号：US11593070B2

公开(公告)日：2023-02-28

申请号：US16814479

申请日：2020-03-10

Applicant: KABUSHIKI KAISHA TOSHIBA

Inventor： Rie Sato ,  Koichi Mizushima

IPC: G06F7/57 ,  G06N3/04 ,  G06N3/063 ,  G11C11/407 ,  H01L27/108 ,  G06N3/049

Abstract: According to one embodiment, an arithmetic device includes an arithmetic circuit. The arithmetic circuit includes a memory part including a plurality of memory regions, and an arithmetic part. One of the memory regions includes a capacitance including a first terminal, and a first electrical circuit electrically connected to the first terminal and configured to output a voltage signal corresponding to a potential of the first terminal.

公开(公告)号：US11580736B2

公开(公告)日：2023-02-14

申请号：US16954068

申请日：2019-01-07

Applicant: DeepMind Technologies Limited

Inventor： Simon Osindero ,  Joao Carreira ,  Viorica Patraucean ,  Andrew Zisserman

IPC: G06V20/40 ,  G06N3/04 ,  G06T1/20 ,  G06N3/049

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for parallel processing of video frames using neural networks. One of the methods includes receiving a video sequence comprising a respective video frame at each of a plurality of time steps; and processing the video sequence using a video processing neural network to generate a video processing output for the video sequence, wherein the video processing neural network includes a sequence of network components, wherein the network components comprise a plurality of layer blocks each comprising one or more neural network layers, wherein each component is active for a respective subset of the plurality of time steps, and wherein each layer block is configured to, at each time step at which the layer block is active, receive an input generated at a previous time step and to process the input to generate a block output.