Related papers: Spiking Cochlea with System-level Local Automatic …

Stochastic Gradient Descent (SGD) is the key learning algorithm for many machine learning tasks. Because of its computational costs, there is a growing interest in accelerating SGD on HPC resources like GPU clusters. However, the…

As the volume of data recorded by embedded edge sensors increases, particularly from neuromorphic devices producing discrete event streams, there is a growing need for hardware-aware neural architectures that enable efficient, low-latency,…

Diffusion models have demonstrated strong generative performance when using guidance methods such as classifier-free guidance (CFG), which enhance output quality by modifying the sampling trajectory. These methods typically improve a target…

Artificial Intelligence-Generated Content (AIGC) refers to the use of AI to automate the information creation process while fulfilling the personalized requirements of users. However, due to the instability of AIGC models, e.g., the…

Recently, deep end-to-end learning has been studied for intent classification in Spoken Language Understanding (SLU). However, end-to-end models require a large amount of speech data with intent labels, and highly optimized models are…

Each round in Differential Private Stochastic Gradient Descent (DPSGD) transmits a sum of clipped gradients obfuscated with Gaussian noise to a central server which uses this to update a global model which often represents a deep neural…

Recently, artificial-intelligence (AI) technologies have been increasingly utilized in a wide range of real-world applications. Speech recognition is one of these practical AI tasks and is regarded as a key application for edge AI systems.…

Spiking Neural Networks (SNNs), providing more realistic neuronal dynamics, have been shown to achieve performance comparable to Artificial Neural Networks (ANNs) in several machine learning tasks. Information is processed as spikes within…

Analog-to-digital conversion (ADC) is a key bottleneck in scaling DSP-centric receiver architectures to multiGigabit/s speeds. Recent information-theoretic results, obtained under ideal channel conditions (perfect synchronization, no…

The global transition from traditional power plants to renewable energy sources introduces new challenges in grid stability, primarily because inverter-based technologies provide insufficient inertia. To address this, we introduce an…

Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performance. In this work, we…

Asynchronous and parallel implementation of standard reinforcement learning (RL) algorithms is a key enabler of the tremendous success of modern RL. Among many asynchronous RL algorithms, arguably the most popular and effective one is the…

Imaging flow cytometry systems aim to analyze a huge number of cells or micro-particles based on their physical characteristics. The vast majority of current systems acquire a large amount of images which are used to train deep artificial…

The extended infomax algorithm for independent component analysis (ICA) can separate sub- and super-Gaussian signals but converges slowly as it uses stochastic gradient optimization. In this paper, an improved extended infomax algorithm is…

Action recognition is an exciting research avenue for artificial intelligence since it may be a game changer in the emerging industrial fields such as robotic visions and automobiles. However, current deep learning faces major challenges…

In modern highly interconnected power grids, automatic generation control (AGC) is crucial in maintaining the stability of the power grid. The dependence of the AGC system on the information and communications technology (ICT) system makes…

Stochastic gradient descent (SGD) is a well known method for regression and classification tasks. However, it is an inherently sequential algorithm at each step, the processing of the current example depends on the parameters learned from…

Training a deep convolutional neural net typically starts with a random initialisation of all filters in all layers which severely reduces the forward signal and back-propagated error and leads to slow and sub-optimal training. Techniques…

A well-designed control-to-display gain function can improve pointing performance with indirect pointing devices like trackpads. However, the design of gain functions is challenging and mostly based on trial and error. AutoGain is a novel…

We consider straggler-resilient learning. In many previous works, e.g., in the coded computing literature, straggling is modeled as random delays that are independent and identically distributed between workers. However, in many practical…