Related papers: Hardware architecture and routing-aware training f…

In view of the performance limitations of fully-decoupled designs for neural architectures and accelerators, hardware-software co-design has been emerging to fully reap the benefits of flexible design spaces and optimize neural network…

The widespread integration of embedded systems across various industries has facilitated seamless connectivity among devices and bolstered computational capabilities. Despite their extensive applications, embedded systems encounter…

A fundamental step in the development of machine learning models commonly involves the tuning of hyperparameters, often leading to multiple model training runs to work out the best-performing configuration. As machine learning tasks and…

Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature…

Spiking neural networks (SNNs) have shown a potential for having low energy with unsupervised learning capabilities due to their biologically-inspired computation. However, they may suffer from accuracy degradation if their processing is…

Intelligent routing plays a key role in modern communication infrastructure, including data centers, computing networks, and future 6G networks. Although reinforcement learning (RL) has shown great potential for intelligent routing, its…

Learned optimizers are a crucial component of meta-learning. Recent advancements in scalable learned optimizers have demonstrated their superior performance over hand-designed optimizers in various tasks. However, certain characteristics of…

With a growing need to enable intelligence in embedded devices in the Internet of Things (IoT) era, secure hardware implementation of Deep Neural Networks (DNNs) has become imperative. We will focus on how to address adversarial robustness…

Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often trained with proxy rewards that only approximate the true objective, leaving them…

Districting-and-routing is a strategic problem aiming to aggregate basic geographical units (e.g., zip codes) into delivery districts. Its goal is to minimize the expected long-term routing cost of performing deliveries in each district…

Advances in novel hardware devices and architectures allow Spiking Neural Network evaluation using ultra-low power, mixed-signal, memristor crossbar arrays. As individual network sizes quickly scale beyond the dimensional capabilities of…

Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods…

One of the challenges of modern neuroscience is creating a "living computer" based on neural networks grown in vitro. Such an artificial device is supposed to perform neurocomputational tasks and interact with the environment when embodied…

Transformer encoders are widely deployed in large-scale web services for natural language understanding tasks such as text classification, semantic retrieval, and content ranking. However, their high inference latency and memory consumption…

Neuromorphic computing aims to replicate the brain's capabilities for energy efficient and parallel information processing, promising a solution to the increasing demand for faster and more efficient computational systems. Efficient…

The adoption of machine learning-based techniques for analog integrated circuit layout, unlike its digital counterpart, has been limited by the stringent requirements imposed by electric and problem-specific constraints, along with the…

Development of routing algorithms is of clear importance as the volume of Internet traffic continues to increase. In this survey, there is much research into how Machine Learning techniques can be employed to improve the performance and…

Parallel training of neural networks at scale is challenging due to significant overheads arising from communication. Recently, deep learning researchers have developed a variety of pruning algorithms that are capable of pruning (i.e.…

Recent advances in algorithm-hardware co-design for deep neural networks (DNNs) have demonstrated their potential in automatically designing neural architectures and hardware designs. Nevertheless, it is still a challenging optimization…

The rapid growth of deep learning models has increased the demand for efficient distributed training strategies. Fully sharded approaches like ZeRO-3 and FSDP partition model parameters across GPUs and apply optimizations such as…