Related papers: Bridging the Accuracy Gap for 2-bit Quantized Neur…
We introduce a Power-of-Two low-bit post-training quantization(PTQ) method for deep neural network that meets hardware requirements and does not call for long-time retraining. Power-of-Two quantization can convert the multiplication…
Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged for their deployments to resource-limited devices. Although recent studies have successfully discretized a full-precision…
Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing methods adopt weight pruning or low-bit quantization individually, often resulting in suboptimal compression rates to…
Deep Learning Architectures employ heavy computations and bulk of the computational energy is taken up by the convolution operations in the Convolutional Neural Networks. The objective of our proposed work is to reduce the energy…
Quantization enables efficient acceleration of deep neural networks by reducing model memory footprint and exploiting low-cost integer math hardware units. Quantization maps floating-point weights and activations in a trained model to…
Modern iterations of deep learning models contain millions (billions) of unique parameters, each represented by a b-bit number. Popular attempts at compressing neural networks (such as pruning and quantisation) have shown that many of the…
Quantization Neural Networks (QNN) have attracted a lot of attention due to their high efficiency. To enhance the quantization accuracy, prior works mainly focus on designing advanced quantization algorithms but still fail to achieve…
Compute-in-memory (CIM) accelerators have emerged as a promising way for enhancing the energy efficiency of convolutional neural networks (CNNs). Deploying CNNs on CIM platforms generally requires quantization of network weights and…
We present QNNRepair, the first method in the literature for repairing quantized neural networks (QNNs). QNNRepair aims to improve the accuracy of a neural network model after quantization. It accepts the full-precision and weight-quantized…
The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning…
Low bit-width integer weights and activations are very important for efficient inference, especially with respect to lower power consumption. We propose Monte Carlo methods to quantize the weights and activations of pre-trained neural…
The post-training quantization (PTQ) challenge of bringing quantized neural net accuracy close to original has drawn much attention driven by industry demand. Many of the methods emphasize optimization of a specific degree-of-freedom (DoF),…
We present accumulator-aware quantization (A2Q), a novel weight quantization method designed to train quantized neural networks (QNNs) to avoid overflow when using low-precision accumulators during inference. A2Q introduces a unique…
Improving the hardware efficiency of deep neural network (DNN) accelerators with techniques such as quantization and sparsity enhancement have shown an immense promise. However, their inference accuracy in non-ideal real-world settings…
Post-training quantization attracts increasing attention due to its convenience in deploying quantized neural networks. Although rounding-to-nearest remains the prevailing method for DNN quantization, prior research has demonstrated its…
Model quantization is widely applied for compressing and accelerating deep neural networks (DNNs). However, conventional Quantization-Aware Training (QAT) focuses on training DNNs with uniform bit-width. The bit-width settings vary across…
Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the…
Large Language Models (LLMs) are proficient in natural language processing tasks, but their deployment is often restricted by extensive parameter sizes and computational demands. This paper focuses on post-training quantization (PTQ) in…
Exploring the expected quantizing scheme with suitable mixed-precision policy is the key point to compress deep neural networks (DNNs) in high efficiency and accuracy. This exploration implies heavy workloads for domain experts, and an…
Weight quantization is one of the most important techniques of Deep Neural Networks (DNNs) model compression method. A recent work using systematic framework of DNN weight quantization with the advanced optimization algorithm ADMM…