Related papers: End-to-End Memristive HTM System for Pattern Recog…

In this paper, we propose a novel ensembling technique for deep neural networks, which is able to drastically reduce the required memory compared to alternative approaches. In particular, we propose to extract multiple sub-networks from a…

While existing studies have highlighted the advantages of deep learning (DL)-based joint source-channel coding (JSCC) schemes in enhancing transmission efficiency, they often overlook the crucial aspect of resource management during the…

Predicting Internet round-trip time (RTT) is critical for routing optimization, quality-of-service (QoS) provisioning, and traffic engineering, yet remains challenging due to long-term temporal dependencies, evolving routing dynamics, and…

Deploying pretrained visual models in real-world environments often suffers from significant performance degradation due to the diversity of testing scenarios. Continuous adaptation of learning models on edge devices via unlabeled data…

The ability to quickly learn new knowledge (e.g. new classes or data distributions) is a big step towards human-level intelligence. In this paper, we consider scenarios that require learning new classes or data distributions quickly and…

Mixed-precision quantization, where a deep neural network's layers are quantized to different precisions, offers the opportunity to optimize the trade-offs between model size, latency, and statistical accuracy beyond what can be achieved…

Semi-supervised learning algorithms typically construct a weighted graph of data points to represent a manifold. However, an explicit graph representation is problematic for neural networks operating in the online setting. Here, we propose…

Extremely increased unstructured data brought by the large-scale intelligent sensing devices application have big challenges not only in data storing and processing but also power consumption surging. Therefore, to improve energy efficiency…

In this paper, the foundations of neuromorphic computing, spiking neural networks (SNNs) and memristors, are analyzed and discussed. Neuromorphic computing is then applied to FPGA design for digital signal processing (DSP). Finite impulse…

Network embedding, which aims to learn low-dimensional representations of nodes, has been used for various graph related tasks including visualization, link prediction and node classification. Most existing embedding methods rely solely on…

Multivariate time series is prevalent in many scientific and industrial domains. Modeling multivariate signals is challenging due to their long-range temporal dependencies and intricate interactions--both direct and indirect. To confront…

The complex nature of real-world problems calls for heterogeneity in both machine learning (ML) models and hardware systems. The heterogeneity in ML models comes from multi-sensor perceiving and multi-task learning, i.e., multi-modality…

Video analytics pipelines have steadily shifted to edge deployments to reduce bandwidth overheads and privacy violations, but in doing so, face an ever-growing resource tension. Most notably, edge-box GPUs lack the memory needed to…

Neuromorphic computing systems overcome the limitations of traditional von Neumann computing architectures. These computing systems can be further improved upon by using emerging technologies that are more efficient than CMOS for neural…

End-to-end learning has become a widely applicable and studied problem in training predictive ML models to be aware of their impact on downstream decision-making tasks. These end-to-end models often outperform traditional methods that…

This article explores the design and experimentation of a neural network architecture capable of dynamically adjusting its internal structure based on the input data. The proposed model introduces a routing mechanism that allows each layer…

The emerging brain-inspired computing paradigm known as hyperdimensional computing (HDC) has been proven to provide a lightweight learning framework for various cognitive tasks compared to the widely used deep learning-based approaches.…

This paper presents StereoNet, the first end-to-end deep architecture for real-time stereo matching that runs at 60 fps on an NVidia Titan X, producing high-quality, edge-preserved, quantization-free disparity maps. A key insight of this…

The traditional approach to distributed machine learning is to adapt learning algorithms to the network, e.g., reducing updates to curb overhead. Networks based on intelligent edge, instead, make it possible to follow the opposite approach,…

Building on our recent research on neural heuristic quantization systems, results on learning quantized motions and resilience to channel dropouts are reported. We propose a general emulation problem consistent with the neuromimetic…