Related papers: VLSI Extreme Learning Machine: A Design Space Expl…

Short-term traffic volume prediction models have been extensively studied in the past few decades. However, most of the previous studies only focus on single-value prediction. Considering the uncertain and chaotic nature of the…

The capacity of a learning machine is measured by its Vapnik-Chervonenkis dimension, and learning machines with a low VC dimension generalize better. It is well known that the VC dimension of SVMs can be very large or unbounded, even though…

The modern power system is evolving with increasing penetration of power electronics introducing complicated electromagnetic phenomenon. Electromagnetic transient (EMT) simulation is essential to understand power system behavior under…

We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidirectional images. Equirectangular projection (ERP) images,…

Although deep learning models are highly effective for various learning tasks, their high computational costs prohibit the deployment to scenarios where either memory or computational resources are limited. In this paper, we focus on…

Scaling large language models (LLMs) significantly improves performance but comes with prohibitive computational costs. Mixture-of-Experts (MoE) models offer an efficient alternative, increasing capacity without a proportional rise in…

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel…

With the rapid expansion of cloud computing infrastructure, energy consumption has become a critical challenge, driving the need for accurate and efficient prediction models. This study proposes a novel Vector Weighted Average Kernel…

Dataset condensation, a concept within data-centric learning, efficiently transfers critical attributes from an original dataset to a synthetic version, maintaining both diversity and realism. This approach significantly improves model…

In this paper, we present power emulation, a novel design paradigm that utilizes hardware acceleration for the purpose of fast power estimation. Power emulation is based on the observation that the functions necessary for power estimation…

Long Short-Term Memory (LSTM) is widely used in various sequential applications. Complex LSTMs could be hardly deployed on wearable and resourced-limited devices due to the huge amount of computations and memory requirements. Binary LSTMs…

The rapid development of Artificial Intelligence (AI) and Internet of Things (IoT) increases the requirement for edge computing with low power and relatively high processing speed devices. The Computing-In-Memory(CIM) schemes based on…

Despite the increasing prevalence of large language models (LLMs), we still have a limited understanding of how their representational spaces are structured. This limits our ability to interpret how and what they learn or relate them to…

The ubiquity of machine learning (ML) and the demand for ever-larger models bring an increase in energy consumption and environmental impact. However, little is known about the energy scaling laws in ML, and existing research focuses on…

Printed Electronics (PE) provide a mechanically flexible and cost-effective solution for machine learning (ML) circuits, compared to silicon-based technologies. However, due to large feature sizes, printed classifiers are limited by high…

The current state of the art of Simultaneous Localisation and Mapping, or SLAM, on low power embedded systems is about sparse localisation and mapping with low resolution results in the name of efficiency. Meanwhile, research in this field…

Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency, or fine-tune smaller…

Multi-Chip-Modules (MCMs) reduce the design and fabrication cost of machine learning (ML) accelerators while delivering performance and energy efficiency on par with a monolithic large chip. However, ML compilers targeting MCMs need to…

We present an alternative to the pseudo-inverse method for determining the hidden to output weight values for Extreme Learning Machines performing classification tasks. The method is based on linear discriminant analysis and provides Bayes…

This work demonstrates a hardware-efficient support vector machine (SVM) training algorithm via the alternative direction method of multipliers (ADMM) optimizer. Low-rank approximation is exploited to reduce the dimension of the kernel…