Related papers: Spiking Cochlea with System-level Local Automatic …
For dynamic visible light communication (VLC) systems, received optical power fluctuates largely due to the fast movement of VLC terminals. Such fluctuations will cause possible signal clipping and quantization noise at the…
In this paper, we propose a novel adaptive technique that uses an attention-based gated scaling (AGS) scheme to improve deep feature learning for connectionist temporal classification (CTC) acoustic modeling. In AGS, the outputs of each…
To stabilize the training of Large Language Models (LLMs), gradient clipping is a nearly ubiquitous heuristic used to alleviate exploding gradients. However, traditional global norm clipping erroneously presupposes gradient homogeneity…
Loss spikes remain a persistent obstacle in large-scale language model pretraining. While previous research has attempted to identify the root cause of loss spikes by investigating individual factors, we observe that, in practice, such…
Spiking silicon cochlea sensors encode sound as an asynchronous stream of spikes from different frequency channels. The lack of labeled training datasets for spiking cochleas makes it difficult to train deep neural networks on the outputs…
Spiking neural networks (SNNs) are emerging as an energy-efficient alternative to traditional artificial neural networks (ANNs) due to their unique spike-based event-driven nature. Coding is crucial in SNNs as it converts external input…
One of the frontier issues that severely hamper the development of automatic snore sound classification (ASSC) associates to the lack of sufficient supervised training data. To cope with this problem, we propose a novel data augmentation…
Localizing acoustic sound sources in the ocean is a challenging task due to the complex and dynamic nature of the environment. Factors such as high background noise, irregular underwater geometries, and varying acoustic properties make…
In this paper we propose a co-design of the secondary frequency regulation in systems of AC microgrids and its cyber securty solutions. We term the secondary frequency regulator a Micro-Automatic Generation Control (Micro-AGC) for…
The gain of neurons' responses in the auditory cortex is sensitive to contrast changes in the stimulus within a spectrotemporal range similar to their receptive fields, which can be interpreted to represent the tuning of the input to a…
Interpretation of electrocardiography (ECG) signals is required for diagnosing cardiac arrhythmia. Recently, machine learning techniques have been applied for automated computer-aided diagnosis. Machine learning tasks can be divided into…
This paper describes a receiver that uses an innovative method to predict, according to history of receiver operating metrics (packet lost/well received), the optimum automatic gain control (AGC) index or most appropriate variable gain…
Learning Classifier Systems (LCS) are population-based reinforcement learners that were originally designed to model various cognitive phenomena. This paper presents an explicitly cognitive LCS by using spiking neural networks as…
The rapid evolution of generative AI, from GANs to modern diffusion models, has resulted in increasingly subtle discriminative clues. These fine-grained signals are often overshadowed by dominant, high-fidelity image content (e.g., the main…
Spiking Neural Networks (SNNs) have been recently integrated into Transformer architectures due to their potential to reduce computational demands and to improve power efficiency. Yet, the implementation of the attention mechanism using…
Previous research has shown that constraining the gradient of loss function with respect to model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed optimal threshold for…
Homeostatic plasticity is a stabilizing mechanism that allows neural systems to maintain their activity around a functional operating point. This is an extremely useful mechanism for neuromorphic computing systems, as it can be used to…
This paper presents an automated method for optimizing parameters in analog/high-frequency circuits, aiming to maximize performance parameters of a radio-frequency (RF) receiver. The design target includes a reduction of power consumption…
Superconducting quantum computers (SQC) can solve some specific problems which are deeply believed to be intractable for classical computers. The control and measurement of qubits can't go on without the synchronous operation of…
Generating long sequences with structural coherence remains a fundamental challenge for autoregressive models across sequential generation tasks. In symbolic music generation, this challenge is particularly pronounced, as existing methods…