Related papers: Encoding Event-Based Data With a Hybrid SNN Guided…

Edge AI applications increasingly require ultra-low-power, low-latency inference. Neuromorphic computing based on event-driven spiking neural networks (SNNs) offers an attractive path, but practical deployment on resource-constrained…

Neuromorphic Computing (NC) and Spiking Neural Networks (SNNs) in particular are often viewed as the next generation of Neural Networks (NNs). NC is a novel bio-inspired paradigm for energy efficient neural computation, often relying on…

We propose a sequential variational autoencoder to learn disentangled representations of sequential data (e.g., videos and audios) under self-supervision. Specifically, we exploit the benefits of some readily accessible supervisory signals…

The key idea of variational auto-encoders (VAEs) resembles that of traditional auto-encoder models in which spatial information is supposed to be explicitly encoded in the latent space. However, the latent variables in VAEs are vectors,…

Estimation of uncertainty in deep learning models is of vital importance, especially in medical imaging, where reliance on inference without taking into account uncertainty could lead to misdiagnosis. Recently, the probabilistic Variational…

Spiking Neural Networks (SNNs) have emerged as an attractive alternative to traditional deep learning frameworks, since they provide higher computational efficiency in event driven neuromorphic hardware. However, the state-of-the-art (SOTA)…

This study examines the challenges of modeling complex and noisy data related to socioeconomic factors over time, with a focus on data from various districts in Odisha, India. Traditional time-series models struggle to capture both trends…

In this paper we propose Structuring AutoEncoders (SAE). SAEs are neural networks which learn a low dimensional representation of data which are additionally enriched with a desired structure in this low dimensional space. While traditional…

Existing formal verification methods for image-based neural network controllers in autonomous vehicles often struggle with high-dimensional inputs, computational inefficiency, and a lack of explainability. These challenges make it difficult…

Spiking Neural Networks (SNNs) represent a biologically inspired paradigm offering an energy-efficient alternative to conventional artificial neural networks (ANNs) for Computer Vision (CV) applications. This paper presents a systematic…

The deployment of Artificial Intelligence on edge devices (TinyML) is often constrained by the high power consumption and latency associated with traditional Artificial Neural Networks (ANNs) and their reliance on intensive Matrix-Multiply…

Deep convolutional neural networks (CNNs) have proven highly effective for visual recognition, where learning a universal representation from activations of convolutional layer plays a fundamental problem. In this paper, we present Fisher…

Event cameras offer high temporal resolution and dynamic range with minimal motion blur, making them promising for robust object detection. While Spiking Neural Networks (SNNs) on neuromorphic hardware are often considered for…

Event-based vision sensors encode local pixel-wise brightness changes in streams of events rather than image frames and yield sparse, energy-efficient encodings of scenes, in addition to low latency, high dynamic range, and lack of motion…

Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning…

Variational Auto-Encoders (VAEs) have emerged as powerful probabilistic models for generative tasks. However, their convergence properties have not been rigorously proven. The challenge of proving convergence is inherently difficult due to…

We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the…

Achieving optimal semantic segmentation with frame-based vision sensors poses significant challenges for real-time systems like UAVs and self-driving cars, which require rapid and precise processing. Traditional frame-based methods often…

Distributed learning and Edge AI necessitate efficient data processing, low-latency communication, decentralized model training, and stringent data privacy to facilitate real-time intelligence on edge devices while reducing dependency on…

Event-based vision sensors achieve up to three orders of magnitude better speed vs. power consumption trade off in high-speed control of UAVs compared to conventional image sensors. Event-based cameras produce a sparse stream of events that…