Samsung Electronics Co., Ltd.

Universitaet Zuerich

University of Zürich

Shih-Chii Liu

Daniel Neil

Tobi Delbruck

Jun Haeng Lee

Michael Pfeiffer

Enea Ceolini

Stefan Braun

Jithendar Anumula

Chenghan Li

Christian Brandli

Bodo Ruckauer

Chang Gao

Xi Chen

Hongjie Liu

Bodo Rueckauer

Disclosed is a neural network-based inference method and apparatus. The neural network-based inference method includes compressing a matrix comprising processing elements corresponding to an operation of a neural network, balancing workloads related to the operation by reordering the compressed matrix based on the workloads, and performing inference based on the reordered matrix.

Neural network-based inference method and apparatus

A processor-implemented neural network method includes: determining a reference sample among sequential input samples to be processed by a neural network, the neural network comprising an input layer, one or more hidden layers, and an output layer; performing an inference process of obtaining an output activation of the output layer based on operations in the hidden layers corresponding to the reference sample input to the input layer; determining layer contraction parameters for determining an affine transformation relationship between the input layer and the output layer, for approximation of the inference process; and performing inference on one or more other sequential input samples among the sequential input samples using affine transformation based on the layer contraction parameters determined with respect to the reference sample.

Method and apparatus with neural network layer contraction

A sensor transformation attention network (STAN) model including sensors configured to collect input signals, attention modules configured to calculate attention scores of feature vectors corresponding to the input signals, a merge module configured to calculate attention values of the attention scores, and generate a merged transformation vector based on the attention values and the feature vectors, and a task-specific module configured to classify the merged transformation vector is provided.

Sensor transformation attention network (STAN) model

A method for operating an artificial neuron and an apparatus for performing the method are provided. The artificial neuron may calculate a change amount of an activation based on an input signal received via an input synapse, determine whether an event occurs in response to the calculated change amount of the activation, and transmit, to an output synapse, an output signal that corresponds to the event in response to an occurrence of the event.

Method for recurrent neural network parameter calculations for utilization of sparsity and apparatus performing same method

Method for determining neuron events based on cluster activations and apparatus performing same method

A processor-implemented neural network method includes acquiring connection weight of an analog neural network (ANN) node of a pre-trained ANN; and determining, a firing rate of a spiking neural network (SNN) node of an SNN, corresponding to the ANN node, based on an activation of the ANN node which is determined based on the connection weight. and the firing rate is also determined based on information indicating a timing at which the SNN node initially fires.

Neural network apparatus and method

A sensor transformation attention network (STAN) model including sensors, attention modules, a merge module and a task-specific module is provided. The attention modules calculate attention scores of feature vectors corresponding to the input signals collected by the sensors. The merge module calculates attention values of the attention scores, and generates a merged transformation vector based on the attention values and the feature vectors. The task-specific module classifies the merged transformation vector.

Method for neural network and apparatus performing same method

A recurrent neural network including an input layer, a hidden layer, and an output layer, wherein the hidden layer includes hybrid memory cell units, each of the hybrid memory cell units including a first memory cells of a first type, the first memory cells being configured to remember a first cell state value fed back to each of gates to determine a degree to which each of the gates is open or closed, and configured to continue to update the first cell state value, and a second memory cells of a second type, each second memory cell of the second memory cells including a first time gate configured to control a second cell state value of the second memory cell based on phase signals of an oscillatory frequency, and a second time gate configured to control an output value of the second memory cell based on the phase signals, and each second memory cell of the second memory cells being configured to remember the second cell state value.

Hybrid memory cell unit and recurrent neural network including hybrid memory cell units

An event-based sensor is provided and may include a sensor configured to generate an event signal that includes identification information that relates to an active pixel that detects an event from among a plurality of sensing pixels, a determiner configured to determine whether the event signal is to be filtered based on a predetermined condition, and an outputter configured to output the event signal based on a result of the determination.

Event-based sensor and operating method of processor

A memory cell unit and a recurrent neural network including memory cell units are provided. The memory cell unit includes a first time gate configured to control a cell state value of the memory cell unit, based on a phase signal of an oscillatory frequency, and a second time gate configured to control an output value of the memory cell unit, based on the phase signal.

Growing community of inventors

Zurich, Switzerland

Shih-Chii Liu