Related papers: A Runtime-Adaptive Transformer Neural Network Acce…

RWKV is a modern RNN architecture that approaches the performance of Transformers, with the advantage of processing long contexts at a linear memory cost. However, its sequential computation pattern struggles to efficiently leverage GPU…

3D reconstruction from videos has become increasingly popular for various applications, including navigation for autonomous driving of robots and drones, augmented reality (AR), and 3D modeling. This task often combines traditional…

Transformers have emerged as a powerful tool for natural language processing (NLP) and computer vision. Through the attention mechanism, these models have exhibited remarkable performance gains when compared to conventional approaches like…

Large Language Models (LLMs) are computationally intensive, particularly during inference. Neuron-adaptive techniques, which selectively activate neurons in Multi-Layer Perceptron (MLP) layers, offer some speedups but suffer from…

Today, artificial neural networks are one of the major innovators pushing the progress of machine learning. This has particularly affected the development of neural network accelerating hardware. However, since most of these architectures…

Neural Radiance Fields (NeRF), an AI-driven approach for 3D view reconstruction, has demonstrated impressive performance, sparking active research across fields. As a result, a range of advanced NeRF models has emerged, leading on-device…

Depth-adaptive neural networks can dynamically adjust depths according to the hardness of input words, and thus improve efficiency. The main challenge is how to measure such hardness and decide the required depths (i.e., layers) to conduct.…

Transformer-based models are the state-of-the-art for Natural Language Understanding (NLU) applications. Models are getting bigger and better on various tasks. However, Transformer models remain computationally challenging since they are…

A new architecture of CNN hardware accelerator is presented. Convolutional Neural Networks (CNNs) are a subclass of neural networks that have demonstrated outstanding performance in a variety of computer vision applications, including…

Convolutional neural network (CNN) dataflow inference accelerators implemented in Field Programmable Gate Arrays (FPGAs) have demonstrated increased energy efficiency and lower latency compared to CNN execution on CPUs or GPUs. However, the…

Many applications are increasingly requiring numerical simulations for solving complex problems. Most of these numerical algorithms are massively parallel and often implemented on parallel high-performance computers. However, classic…

Deep Forest is a prominent machine learning algorithm known for its high accuracy in forecasting. Compared with deep neural networks, Deep Forest has almost no multiplication operations and has better performance on small datasets. However,…

Designing and implementing efficient, provably correct parallel neural network processing is challenging. Existing high-level parallel abstractions like MapReduce are insufficiently expressive while low-level tools like MPI and Pthreads…

Ternary neural networks (TNNs) offer a superior accuracy-energy trade-off compared to binary neural networks. However, until now, they have required specialized accelerators to realize their efficiency potential, which has hindered…

Deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems. At the same time, the computational complexity and resource consumption of these networks also…

Deep learning has significantly advanced the state of the art in artificial intelligence, gaining wide popularity from both industry and academia. Special interest is around Convolutional Neural Networks (CNN), which take inspiration from…

Tensor accelerators now represent a growing share of compute resources in modern CPUs and GPUs. However, they are hard to program, leading developers to use vendor-provided kernel libraries that support tensor accelerators. As a result, the…

The deep learning accelerator is one of the methods to accelerate deep learning network computations, which is mainly based on convolutional neural network acceleration. To address the fact that concurrent convolutional neural network…

Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC---called a Tensor Processing Unit (TPU)---deployed in datacenters since 2015 that…

Hardware accelerators are essential for achieving low-latency, energy-efficient inference in edge applications like image recognition. Spiking Neural Networks (SNNs) are particularly promising due to their event-driven and temporally sparse…