Search Results for author:
Found 9 papers, 0 papers with code
Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs
The Winograd or Cook-Toom class of algorithms help to reduce the overall compute complexity of many modern deep convolutional neural networks (CNNs).
Compressing RNNs for IoT devices by 15-38x using Kronecker Products
Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size. As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy.
Run-Time Efficient RNN Compression for Inference on Edge Devices
Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints.
Pushing the limits of RNN Compression
This paper introduces a method to compress RNNs for resource constrained environments using Kronecker product (KP).
Ternary MobileNets via Per-Layer Hybrid Filter Banks
Using this proposed quantization method, we quantized a substantial portion of weight filters of MobileNets to ternary values resulting in 27. 98% savings in energy, and a 51. 07% reduction in the model size, while achieving comparable accuracy and no degradation in throughput on specialized hardware in comparison to the baseline full-precision MobileNets.
Compressing Language Models using Doped Kronecker Products
Kronecker Products (KP) have been used to compress IoT RNN Applications by 15-38x compression factors, achieving better results than traditional compression methods.
High Throughput Matrix-Matrix Multiplication between Asymmetric Bit-Width Operands
While existing SIMD matrix multiplication instructions for symmetric bit-width operands can support operands of mixed precision by zero- or sign-extending the narrow operand to match the size of the other operands, they cannot exploit the benefit of narrow bit-width of one of the operands.
BIG-bench Machine Learning
Vocal Bursts Intensity Prediction
Rank and run-time aware compression of NLP Applications
We evaluate the impact of this technique on 5 NLP benchmarks across multiple tasks (Translation, Intent Detection, Language Modeling) and show that for similar accuracy values and compression factors, HMF can achieve more than 2. 32x faster inference run-time than pruning and 16. 77% better accuracy than LMF.
Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices
Additionally, results with doped kronecker product matrices demonstrate state-of-the-art accuracy at large compression factors (10 - 25x) across 4 natural language processing applications with minor loss in accuracy.
