Related papers: Hardware Architecture for Large Parallel Array of …

The human brain simultaneously optimizes synaptic weights and topology by growing, pruning, and strengthening synapses while performing all computation entirely in memory. In contrast, modern artificial-intelligence systems separate weight…

In this work, we present a random forest framework that learns the weights, shapes, and sparsities of feature representations for real-time semantic segmentation. Typical filters (kernels) have predetermined shapes and sparsities and learn…

This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance…

This paper studies the generalization properties of a recently proposed kernel method, the Random Feature models with Learnable Activation Functions (RFLAF). By applying a data-dependent sampling scheme for generating features, we provide…

In this technical report, we explore the behavior of Recursive Feature Machines (RFMs), a type of novel kernel machine that recursively learns features via the average gradient outer product, through a series of experiments on regression…

Limiting failures of machine learning systems is of paramount importance for safety-critical applications. In order to improve the robustness of machine learning systems, Distributionally Robust Optimization (DRO) has been proposed as a…

We propose a hardware efficient quantum residual neural network which implements residual connections through a deterministic mixture of the identity operation and variational unitaries, enabling fully differentiable training. In contrast…

Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during…

With the popularity of mobile devices, e.g., smartphone and wearable devices, lighter and faster model is crucial for the application of video super resolution. However, most previous lightweight models tend to concentrate on reducing…

Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation…

Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devices, but existing training methods for these compact models…

Large Language Models (LLMs) deployed on edge devices learn through fine-tuning and updating a certain portion of their parameters. Although such learning methods can be optimized to reduce resource utilization, the overall required…

Neuromorphic Multiply-And-Accumulate (MAC) circuits utilizing synaptic weight elements based on SRAM or novel Non-Volatile Memories (NVMs) provide a promising approach for highly efficient hardware representations of neural networks. NVM…

Deep learning based approaches has achieved great performance in single image super-resolution (SISR). However, recent advances in efficient super-resolution focus on reducing the number of parameters and FLOPs, and they aggregate more…

The inverse-free extreme learning machine (ELM) algorithm proposed in [4] was based on an inverse-free algorithm to compute the regularized pseudo-inverse, which was deduced from an inverse-free recursive algorithm to update the inverse of…

Operator learning is a data-driven approximation of mappings between infinite-dimensional function spaces, such as the solution operators of partial differential equations. Kernel-based operator learning can offer accurate, theoretically…

The rapid proliferation of wireless devices makes robust identity authentication essential. Radio Frequency Fingerprinting (RFF) exploits device-specific, hard-to-forge physical-layer impairments for identification, and is promising for IoT…

Recent progress in learning-based image compression has demonstrated that end-to-end optimization can substantially outperform traditional codecs by jointly learning compact latent representations and probabilistic entropy models. However,…

Low-Power Edge-AI capabilities are essential for on-device extended reality (XR) applications to support the vision of Metaverse. In this work, we investigate two representative XR workloads: (i) Hand detection and (ii) Eye segmentation,…

Image classification remains a fundamental yet challenging task in computer vision, particularly when fine-grained feature extraction and background noise suppression are required simultaneously. Conventional convolutional neural networks,…