Related papers: Minimize Quantization Output Error with Bias Compe…

Mixed-precision quantization, where a deep neural network's layers are quantized to different precisions, offers the opportunity to optimize the trade-offs between model size, latency, and statistical accuracy beyond what can be achieved…

In neural network binarization, BinaryConnect (BC) and its variants are considered the standard. These methods apply the sign function in their forward pass and their respective gradients are backpropagated to update the weights. However,…

Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription accuracy. However, the biasing mechanism is typically based on a cross-attention module between the…

Binary neural networks (BNNs), where both weights and activations are binarized into 1 bit, have been widely studied in recent years due to its great benefit of highly accelerated computation and substantially reduced memory footprint that…

Generative neural image compression supports data representation at extremely low bitrate, synthesizing details at the client and consistently producing highly realistic images. By leveraging the similarities between quantization error and…

Recent one-shot Neural Architecture Search algorithms rely on training a hardware-agnostic super-network tailored to a specific task and then extracting efficient sub-networks for different hardware platforms. Popular approaches separate…

Quantizing deep neural networks ,reducing the precision (bit-width) of their computations, can remarkably decrease memory usage and accelerate processing, making these models more suitable for large-scale medical imaging applications with…

Network quantization significantly reduces model inference complexity and has been widely used in real-world deployments. However, most existing quantization methods have been developed mainly on Convolutional Neural Networks (CNNs), and…

Bayesian Neural Networks (BNNs) offer a principled and natural framework for proper uncertainty quantification in the context of deep learning. They address the typical challenges associated with conventional deep learning methods, such as…

Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of…

Batch Normalization (BN) is a commonly used technique to accelerate and stabilize training of deep neural networks. Despite its empirical success, a full theoretical understanding of BN is yet to be developed. In this work, we analyze BN…

With the development of deep neural networks, the size of network models becomes larger and larger. Model compression has become an urgent need for deploying these network models to mobile or embedded devices. Model quantization is a…

Similar to convolution neural networks, recurrent neural networks (RNNs) typically suffer from over-parameterization. Quantizing bit-widths of weights and activations results in runtime efficiency on hardware, yet it often comes at the cost…

Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that repeat the quantization process and train different models…

Post-training quantization (PTQ) for vision transformers (ViTs) has garnered significant attention due to its efficiency in compressing models. However, existing methods typically overlook the relationship between a well-trained NN and the…

Quantization based model compression serves as high performing and fast approach for inference that yields models which are highly compressed when compared to their full-precision floating point counterparts. The most extreme quantization…

The role of quantization within implicit/coordinate neural networks is still not fully understood. We note that using a canonical fixed quantization scheme during training produces poor performance at low-rates due to the network weight…

Recurrent neural networks have achieved excellent performance in many applications. However, on portable devices with limited resources, the models are often too large to deploy. For applications on the server with large scale concurrent…

Decentralized optimization methods enable on-device training of machine learning models without a central coordinator. In many scenarios communication between devices is energy demanding and time consuming and forms the bottleneck of the…

Channel pruning is a promising technique to compress the parameters of deep convolutional neural networks(DCNN) and to speed up the inference. This paper aims to address the long-standing inefficiency of channel pruning. Most channel…