Samsung Electronics Co., Ltd.

Unist (Ulsan National Institute of Science and Technology )

Ulsan National Institute of Science and Technology

Jongeun Lee

Hyeongseok Yu

Hyeonuk Sim

Sehwan Lee

Sugil Lee

Hyeon Uk Sim

Jooyeon Choi

A processor-implemented method includes determining a first quantization value by performing log quantization on a parameter from one of input activation values and weight values in a layer of a neural network, comparing a threshold value with an error between a first dequantization value obtained by dequantization of the first quantization value and the parameter, determining a second quantization value by performing log quantization on the error in response to the error being greater than the threshold value as a result of the comparing; and quantizing the parameter to a value in which the first quantization value and the second quantization value are grouped.

Method and apparatus with neural network parameter quantization

The present disclosure provides a calculation error correction device including a first learning unit that trains an effective weight value prediction model for outputting an effective weight value matrix by using learning data in response to an input of the random weight value matrix, an effective weight value calculation unit that inputs a first weight value matrix into the effective weight value prediction model to derive the effective weight value matrix, a second learning unit that applies a second input vector to a target neural network as an input value, applied the effective weight value matrix as a weight value, and trains the weight value such that an output vector follows a result of multiplication of the second input vector and the first weight value matrix, and a control unit that performs matrix-vector multiplication by mapping the first input vector and the trained weight value matrix to the resistive memory.

Calculation error correction device and method applied to resistive memory-based neural network accelerator

A processor-implemented neural network operation method includes: receiving a first activation gradient and a first threshold corresponding to a layer included in a neural network; sparsifying the first activation gradient based on the first threshold; determining a second activation gradient by performing a neural network operation based on the sparsified first activation gradient; determining a second threshold by updating the first threshold based on the second activation gradient; and performing a neural network operation based on the second activation gradient and the second threshold.

Method and apparatus with neural network operation using sparsification

A neural network device including an on-chip buffer memory that stores an input feature map of a first layer of a neural network, a computational circuit that receives the input feature map of the first layer through a single port of the on-chip buffer memory and performs a neural network operation on the input feature map of the first layer to output an output feature map of the first layer corresponding to the input feature map of the first layer, and a controller that transmits the output feature map of the first layer to the on-chip buffer memory through the single port to store the output feature map of the first layer and the input feature map of the first layer together in the on-chip buffer memory.

Method and device with neural network implementation

A neural network operation apparatus includes an input register to store an input feature map, a processing element array including a processing element to perform an operation based on the input feature map and a weight matrix, and a controller to map a portion of the input feature map and a portion of the weight matrix, both on which the operation is to be performed, to the processing element.

Neural network operation method and apparatus with mapping orders

A wire bonding includes a capillary that extrudes a wire; a wire clamp assembly disposed on the capillary; a support disposed on the wire clamp assembly; a wire contact member; and a slide rail that provides a slide hole. The wire clamp assembly includes: a first member; a second member spaced apart from the first member; a first contact member coupled to the first member; and a second contact member coupled to the second member and spaced apart from the first contact member. The first member includes a first body that extends in a first direction and a first tilting member that extends at an acute angle relative to the first direction. The second member includes a second body that extends in the first direction and is spaced apart from the first body in a second direction a second tilting member.

Wire bonding apparatus

A neural network device includes: an on-chip buffer memory that stores an input feature map of a first layer of a neural network, a computational circuit that receives the input feature map of the first layer through a single port of the on-chip buffer memory and performs a neural network operation on the input feature map of the first layer to output an output feature map of the first layer corresponding to the input feature map of the first layer, and a controller that transmits the output feature map of the first layer to the on-chip buffer memory through the single port to store the output feature map of the first layer and the input feature map of the first layer together in the on-chip buffer memory.

Disclosed is a wire bonding apparatus comprising a capillary, a wire clamp assembly, and a support. The wire clamp assembly includes a first member, a second member, a first contact member, and a second contact member. The first member includes a first body and a first tilting member. The second member includes a second body and a second tilting member. The first contact member is coupled to an inner surface of the first tilting member and extends in an extending direction of the first tilting member. The second contact member is coupled to an inner surface of the second tilting member and extends in an extending direction of the second tilting member. The second member is movable in the second direction.

Growing community of inventors

Ulsan, South Korea

Jongeun Lee