Related papers: Tiny Classifier Circuits: Evolving Accelerators fo…

Convolutional Neural Networks are extensively used in a wide range of applications, commonly including computer vision tasks like image and video classification, recognition, and segmentation. Recent research results demonstrate that…

Quantum machine learning (QML) is a discipline that seeks to transfer the advantages of quantum computing to data-driven tasks. However, many studies rely on toy datasets or heavy feature reduction, raising concerns about their scalability.…

This paper introduces a new kernel-based classifier by viewing kernel matrices as generalized graphs and leveraging recent progress in graph embedding techniques. The proposed method facilitates fast and scalable kernel matrix embedding,…

Fast model updates for unseen tasks on intelligent edge devices are crucial but also challenging due to the limited computational power. In this paper,we propose MetaLDC, which meta-trains braininspired ultra-efficient low-dimensional…

We study classifiers operating under severe classification time constraints, corresponding to 1-1000 CPU microseconds, using Convolutional Tables Ensemble (CTE), an inherently fast architecture for object category recognition. The…

The fifth generation of cellular networks (5G) will rely on edge cloud deployments to satisfy the ultra-low latency demand of future applications. In this paper, we argue that such deployments can also be used to enable advanced data-driven…

The dominance of large decoder-only language models has overshadowed encoder-decoder architectures, despite their fundamental efficiency advantages in sequence processing. For small language models (SLMs) - those with 1 billion parameters…

On-device machine learning (ML) has become a fundamental component of emerging mobile applications. Adaptive model deployment delivers efficient inference for heterogeneous device capabilities and performance requirements through…

Advancements in ultra-low-power tiny machine learning (TinyML) systems promise to unlock an entirely new class of smart applications. However, continued progress is limited by the lack of a widely accepted and easily reproducible benchmark…

The family of temporal difference (TD) methods span a spectrum from computationally frugal linear methods like TD({\lambda}) to data efficient least squares methods. Least square methods make the best use of available data directly…

Training on edge devices poses several challenges as these devices are generally resource-constrained, especially in terms of power. State-of-the-art techniques at the device level reduce the GPU frequency to enforce power constraints,…

The predictive quality of machine learning models is typically measured in terms of their (approximate) expected prediction accuracy or the so-called Area Under the Curve (AUC). Minimizing the reciprocals of these measures are the goals of…

The rapid updates in error-resilient applications along with their quest for high throughput have motivated designing fast approximate functional units for Field-Programmable Gate Arrays (FPGAs). Studies that proposed imprecise functional…

Widespread development of driverless vehicles has led to the formation of autonomous racing, where technological development is accelerated by the high speeds and competitive environment of motorsport. A particular challenge for an…

Machine learning systems are often used in settings where individuals adapt their features to obtain a desired outcome. In such settings, strategic behavior leads to a sharp loss in model performance in deployment. In this work, we aim to…

In this work, a new method for designing an analog circuit for deep sub-micron CMOS fabrication processes is proposed. The proposed method leverages the regression algorithms with the transistor circuit model to size a transistor in 0.18 um…

Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acute in operational…

Multi-label classification has attracted much attention in the machine learning community to address the problem of assigning single samples to more than one class at the same time. We propose an evolving multi-label fuzzy classifier…

Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition. Existing methods, including the…

A machine learning (ML) design framework is proposed for adaptively adjusting clock frequency based on propagation delay of individual instructions. A random forest model is trained to classify propagation delays in real time, utilizing…