Related papers: TYTAN: Taylor-series based Non-Linear Activation E…

The pervasiveness of "Internet-of-Things" in our daily life has led to a recent surge in fog computing, encompassing a collaboration of cloud computing and edge intelligence. To that effect, deep learning has been a major driving force…

Many edge devices employ Recurrent Neural Networks (RNN) to enhance their product intelligence. However, the increasing computation complexity poses challenges for performance, energy efficiency and product development time. In this paper,…

Deep neural networks (DNN) are increasingly being accelerated on application-specific hardware such as the Google TPU designed especially for deep learning. Timing speculation is a promising approach to further increase the energy…

With the popularity of deep learning, the hardware implementation platform of deep learning has received increasing interest. Unlike the general purpose devices, e.g., CPU, or GPU, where the deep learning algorithms are executed at the…

Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…

The increasing complexity of AI models requires flexible hardware capable of supporting diverse precision formats, particularly for energy-constrained edge platforms. This work presents PARV-CE, a SIMD-enabled, multi-precision MAC engine…

The computation and storage requirements for Deep Neural Networks (DNNs) are usually high. This issue limits their deployability on ubiquitous computing devices such as smart phones, wearables and autonomous drones. In this paper, we…

Architecture plays an important role in deciding the performance of deep neural networks. However, the search for the optimal architecture is often hindered by the vast search space, making it a time-intensive process. Recently, a novel…

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…

Physics-guided deep learning is an important prevalent research topic in scientific machine learning, which has tremendous potential in various complex applications including science and engineering. In these applications, data is expensive…

Deploying Vision Transformers on edge devices is challenging due to their high computational complexity, while full offloading to cloud resources presents significant latency overheads. We propose a novel collaborative inference framework,…

Effective activation functions introduce non-linear transformations, providing neural networks with stronger fitting capa-bilities, which help them better adapt to real data distributions. Huawei Noah's Lab believes that dynamic activation…

In this work, we present a general purpose deep neural network package for representing energies, forces, dipole moments, and polarizabilities of atomistic systems. This so-called recursively embedded atom neural network model takes both…

In this paper, we study deep generative models for effective unsupervised learning. We propose VGAN, which works by minimizing a variational lower bound of the negative log likelihood (NLL) of an energy based model (EBM), where the model…

Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference deployment without significantly compromising model…

Solving stiff ordinary differential equations (StODEs) requires sophisticated numerical solvers, which are often computationally expensive. In general, traditional explicit time integration schemes with restricted time step sizes are not…

Edge computing devices inherently face tight resource constraints, which is especially apparent when deploying Deep Neural Networks (DNN) with high memory and compute demands. FPGAs are commonly available in edge devices. Since these…

This paper investigates the intriguing question of whether we can create learning algorithms that automatically generate training data, learning environments, and curricula in order to help AI agents rapidly learn. We show that such…

Deploying Python-based AI agents on resource-constrained edge devices presents a critical runtime optimization challenge: high thread counts are needed to mask I/O latency, yet Python's Global Interpreter Lock (GIL) serializes execution. We…

Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most. Despite extensive research, there is currently no standardized evaluation…