Related papers: Flexible Bit-Truncation Memory for Approximate App…
Approximate computing is an emerging computing paradigm that offers improved power consumption by relaxing the requirement for full accuracy. Since real-world applications may have different requirements for design accuracy, one trend of…
Processing visual data on mobile devices has many applications, e.g., emergency response and tracking. State-of-the-art computer vision techniques rely on large Deep Neural Networks (DNNs) that are usually too power-hungry to be deployed on…
Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production,…
Researchers and designers are facing problems with memory and power walls, considering the pervasiveness of Von-Neumann architecture in the design of processors and the problems caused by reducing the dimensions of deep sub-micron…
Computing-In-Memory (CIM) offers a potential solution to the memory wall issue and can achieve high energy efficiency by minimizing data movement, making it a promising architecture for edge AI devices. Lightweight models like MobileNet and…
Compute-in-memory (CIM) presents an attractive approach for energy-efficient computing in data-intensive applications. However, the development of suitable memory designs to achieve high-performance CIM remains a challenging task. Here, we…
Optimization problems with an auxiliary latent variable structure in addition to the main model parameters occur frequently in computer vision and machine learning. The additional latent variables make the underlying optimization task…
Byte-addressable persistent memory (B-APM) presents a new opportunity to bridge the performance gap between main memory and storage. In this paper, we present the usage scenarios for this new technology, based on the capabilities of Intel's…
Recent years have seen deep neural networks (DNNs) becoming wider and deeper to achieve better performance in many applications of AI. Such DNNs however require huge amounts of memory to store weights and intermediate results (e.g.,…
Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, these models are extremely memory intensive during their…
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…
Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…
Multi-bit spiking neural networks (SNNs) have recently become a heated research spot, pursuing energy-efficient and high-accurate AI. However, with more bits involved, the associated memory and computation demands escalate to the point…
We propose a new variant of the Adam optimizer called MicroAdam that specifically minimizes memory overheads, while maintaining theoretical convergence guarantees. We achieve this by compressing the gradient information before it is fed…
Deep neural networks are increasingly bottlenecked by the cost of optimization, both in terms of GPU memory and compute time. Existing acceleration techniques, such as mixed precision, second-order methods, and batch size scaling, are…
We study embedded Binarized Neural Networks (eBNNs) with the aim of allowing current binarized neural networks (BNNs) in the literature to perform feedforward inference efficiently on small embedded devices. We focus on minimizing the…
Today's systems are overwhelmingly designed to move data to computation. This design choice goes directly against at least three key trends in systems that cause performance, scalability and energy bottlenecks: (1) data access from memory…
The conventional approach of moving data to the CPU for computation has become a significant performance bottleneck for emerging scale-out data-intensive applications due to their limited data reuse. At the same time, the advancement in 3D…
ATM-Net is a novel neural network architecture tailored for energy-harvested IoT devices, integrating adaptive termination points with multi-precision computing. It dynamically adjusts computational precision (32/8/4-bit) and network depth…
Nowadays, one practical limitation of deep neural network (DNN) is its high degree of specialization to a single task or domain (e.g., one visual domain). It motivates researchers to develop algorithms that can adapt DNN model to multiple…