Related papers: Fuzzy Encoding-Decoding to Improve Spiking Q-Learn…
The transportation of sensitive equipment often suffers from vibrations caused by terrain, weather, and motion speed, leading to inefficiencies and potential damage. To address this challenge, this paper explores an intelligent control…
We present Flex, an efficient and effective scene encoder that addresses the computational bottleneck of processing high-volume multi-camera data in end-to-end autonomous driving. Flex employs a small set of learnable scene tokens to…
With the continuous advancement of processors, modern micro-architecture designs have become increasingly complex. The vast design space presents significant challenges for human designers, making design space exploration (DSE) algorithms a…
The data representation in a machine-learning model strongly influences its performance. This becomes even more important for quantum machine learning models implemented on noisy intermediate scale quantum (NISQ) devices. Encoding high…
We propose a soft gradient boosting framework for sequential regression that embeds a learnable linear feature transform within the boosting procedure. At each boosting iteration, we train a soft decision tree and learn a linear input…
In this paper, we propose a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion based on the U-Net architecture. The proposed method is designed based on two principles, boosting and error feedback, and we show that they are…
The quality of control (QoC) of a resource-constrained embedded control system may be jeopardized in dynamic environments with variable workload. This gives rise to the increasing demand of co-design of control and scheduling. To deal with…
A robust auto-landing problem of a Truss-braced Wing (TBW) regional jet aircraft with poor stability characteristics is presented in this study employing a Fuzzy Reinforcement Learning scheme. Reinforcement Learning (RL) has seen a recent…
Despite recent progress in training spiking neural networks (SNNs) for classification, their application to continuous motor control remains limited. Here, we demonstrate that fully spiking architectures can be trained end-to-end to control…
Single Flux Quantum (SFQ) technology represents a groundbreaking advancement in computational efficiency and ultra-high-speed neuromorphic processing. The key features of SFQ technology, particularly data representation, transmission, and…
Image dehazing is a critical challenge in computer vision, essential for enhancing image clarity in hazy conditions. Traditional methods often rely on atmospheric scattering models, while recent deep learning techniques, specifically…
Spiking neural networks (SNNs), a brain-inspired computing paradigm, are emerging for their inference performance, particularly in terms of energy efficiency and latency attributed to the plasticity in signal processing. To deploy SNNs in…
The advent of neuralmorphic spike cameras has garnered significant attention for their ability to capture continuous motion with unparalleled temporal resolution.However, this imaging attribute necessitates considerable resources for binary…
... This paper is to describe exploratory research on the design of a modular autonomous mobile robot controller. The controller incorporates a fuzzy logic [8] [9] approach for steering and speed control [37], a FL approach for ultrasound…
Efficiently encoding classical visual data into quantum states is essential for realizing practical quantum neural networks (QNNs). However, existing encoding schemes often discard spatial and semantic information when adapting…
Spiking neural networks (SNNs) recently gained momentum due to their low-power multiplication-free computing and the closer resemblance of biological processes in the nervous system of humans. However, SNNs require very long spike trains…
Spiking neural networks (SNNs) have gained considerable interest due to their energy-efficient characteristics, yet lack of a scalable training algorithm has restricted their applicability in practical machine learning problems. The deep…
In recent years, neuromorphic computing and spiking neural networks (SNNs) have ad-vanced rapidly through integration with deep learning. However, the performance of SNNs still lags behind that of convolutional neural networks (CNNs),…
Spiking Vision Transformers (S-ViTs) offer a promising framework for energy-efficient visual learning. However, existing designs remain limited by two fundamental issues: the restricted information capacity of binary spike coding and the…
Task-specific data-fusion networks have marked considerable achievements in urban scene parsing. Among these networks, our recently proposed RoadFormer successfully extracts heterogeneous features from RGB images and surface normal maps and…