Numenta, Inc.

Yesvideo, Inc.

Interval Research Corporation

Electric Planet, Inc.

Other

Interval Licensing LLC

Elet Systems L.l.c.

Siemens Aktiengesellschaft

Fuji Xerox Co., Ltd.

Hewlett-packard Company

Vulcan Patents LLC

Yesvideo.com

Interval Resarch Corporation

Subutai Ahmad

Jeffrey Charles Hawkins

Jeffrey L Edwards

Neal A Bhadkamkar

Ronald Marianetti, Ii

Michele Mae Covell

Anosh Raj

Sai-Wai Fu

Paul A Freiberger

Brygg A Ullmer

Hon Pun Sit

Yuwei Cui

Steve B Cousins

Sadie Louise Honey

Adwait Ullal

Dileep George

Frank Emmanuel Astier

Jonathan R Cohen

Emanuel E Farber

Philippe P Piernot

Chetan Surpur

Christopher D Horner

David Kumar

Luiz Scheinkman

Brett M Keating

Marcus Anthony Lewis

William Cooper Saphir

Katerina L Shiffer

Ronald Marianetti

G Scott France

Jonathan T Foote

John Steven Boreczky

HongJiang Zhang

Kevin L Hunter

Charles Curry

Giyora Sayfan

Michele May Covell

Rolf Schuster

Kevin Lee Hunter

Wiliam C Saphir

Ronald Ii Marianetti

Jeffrey Lane Edwards

A hardware accelerator that is efficient at performing computations related to a sparse neural network. The sparse neural network may be associated with a plurality of nodes. One of the nodes includes one or more sparse tensors. The accelerator may compress the sparse tensor to a dense tensor. The sparse tensor may also be structured so that the dense locations in the tensor are blocked or partitioned. The accelerator may transpose the weight tensor and align the partitions of the tensor with the hardware architecture. The structured tensor has a balanced number of active values so that the active values can be processed by an efficient number of operating cycles of the accelerator. The accelerator may also perform bitwise and operation to determine the location of dense pairs in two sparse tensors to reduce the number of computations.

Hardware architecture for processing data in sparse neural network

An inference system trains and performs inference using a sparse neural network. The sparse neural network may include one or more layers, and each layer may be associated with a set of sparse weights that represent sparse connections between nodes of a layer and nodes of a previous layer. A layer output may be generated by applying the set of sparse weights associated with the layer to the layer output of a previous layer. Moreover, the one or more layers of the sparse neural network may generate sparse layer outputs. By using sparse representations of weights and layer outputs, robustness and stability of the neural network can be significantly improved, while maintaining competitive accuracy.

Performing inference and training using sparse neural network

One or more multi-layer systems are used to perform inference. A multi-layer system may correspond to a node that receives a set of sensory input data for hierarchical processing, and may be grouped to perform processing for sensory input data. Inference systems at lower layers of a multi-layer system pass representation of objects to inference systems at higher layers. Each inference system can perform inference and form their own versions of representations of objects, regardless of the level and layer of the inference systems. The set of candidate objects for each inference system is updated to those consistent with feature-location representations for the sensors as well as object representations at lower layers. The set of candidate objects is also updated to those consistent with candidate objects from other inference systems, such as inference systems at other layers of the hierarchy or inference systems included in other multi-layer systems.

Inferencing and learning based on sensorimotor input data

Embodiments relate to performing inference, such as object recognition, based on sensory inputs received from sensors and location information associated with the sensory inputs. The sensory inputs describe one or more features of the objects. The location information describes known or potential locations of the sensors generating the sensory inputs. An inference system learns representations of objects by characterizing a plurality of feature-location representations of the objects, and then performs inference by identifying or updating candidate objects consistent with feature-location representations observed from the sensory input data and location information. In one instance, the inference system learns representations of objects for each sensor. The set of candidate objects for each sensor is updated to those consistent with candidate objects for other sensors, as well as the observed feature-location representations for the sensor.

Embodiments relate to a processing node in a temporal memory system that performs temporal pooling or processing by activating cells where the activation of a cell is maintained longer if the activation of the cell were previously predicted or activation on more than a certain portion of associated cells in a lower node was correctly predicted. An active cell correctly predicted to be activated or an active cell having connections to lower node active cells that were correctly predicted to become active contribute to accurate prediction, and hence, is maintained active longer than cells activated but were not previously predicted to become active. Embodiments also relate to a temporal memory system for detecting, learning, and predicting spatial patterns and temporal sequences in input data by using action information.

Temporal processing scheme and sensorimotor information processing

Embodiments relate to a first processing node that processes an input data having a temporal sequence of spatial patterns by retaining a higher-level context of the temporal sequence. The first processing node performs temporal processing based at least on feedback inputs received from a second processing node. The first processing node determines whether learned temporal sequences are included in the input data based on sequence inputs transmitted within the same level of a hierarchy of processing nodes and the feedback inputs received from an upper level of the hierarchy of processing nodes.

Feedback mechanisms in sequence learning systems with temporal processing capability

A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.

Sparse distributed representation for networked processing in predictive system

Temporal memory using sparse distributed representation

A web-based hierarchical temporal memory (HTM) system in which one or more client devices communicate with a remote server via a communication network. The remote server includes at least a HTM server for implementing a hierarchical temporal memory (HTM). The client devices generate input data including patterns and sequences, and send the input data to the remote server for processing. The remote server (specifically, the HTM server) performs processing in order to determine the causes of the input data, and sends the results of this processing to the client devices. The client devices need not have processing and/or storage capability for running the HTM but may nevertheless take advantage of the HTM by submitting a request to the HTM server.

Hierarchical temporal memory (HTM) system deployed as web service

Growing community of inventors

Palo Alto, CA, United States of America

Subutai Ahmad