Search Results for author:
Found 6 papers, 0 papers with code
Saving RNN Computations with a Neuron-Level Fuzzy Memoization Scheme
In this paper, we observe that the output of a neuron exhibits small changes in consecutive invocations.~We exploit this property to build a neuron-level fuzzy memoization scheme, which dynamically caches each neuron's output and reuses it whenever it is predicted that the current output will be similar to a previously computed result, avoiding in this way the output computations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
CREW: Computation Reuse and Efficient Weight Storage for Hardware-accelerated MLPs and RNNs
To this end, each weight is replaced offline by an index in the buffer of unique products.
Boosting LSTM Performance Through Dynamic Precision Selection
Based on this observation, we implement a novel hardware scheme that tracks the evolution of the elements in the LSTM cell state and dynamically selects the appropriate precision in each time step.
SHARP: An Adaptable, Energy-Efficient Accelerator for Recurrent Neural Network
To solve these issues, we propose an intelligent tiled-based dispatching mechanism for increasing the adaptiveness of RNN computation, in order to efficiently handle the data dependencies.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
(Pen-) Ultimate DNN Pruning
DNN pruning reduces memory footprint and computational work of DNN-based solutions to improve performance and energy-efficiency.
E-PUR: An Energy-Efficient Processing Unit for Recurrent Neural Networks
The main goal of E-PUR is to support large recurrent neural networks for low-power mobile devices.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
