Search Results for author:
Found 10 papers, 1 papers with code
Cost-Driven Hardware-Software Co-Optimization of Machine Learning Pipelines
We perform this hardware/software co-design from the cost, latency, and user-experience perspective, and develop a set of guidelines for optimal system design and model deployment for the most cost-constrained platforms.
Training Neural Networks for Execution on Approximate Hardware
Approximate computing methods have shown great potential for deep learning.
PhotoFourier: A Photonic Joint Transform Correlator-Based Neural Network Accelerator
The last few years have seen a lot of work to address the challenge of low-latency and high-throughput convolutional neural network inference.
Bit-serial Weight Pools: Compression and Arbitrary Precision Execution of Neural Networks on Resource Constrained Processors
Applications of neural networks on edge systems have proliferated in recent years but the ever-increasing model size makes neural networks not able to deploy on resource-constrained microcontrollers efficiently.
High Throughput Multi-Channel Parallelized Diffraction Convolutional Neural Network Accelerator
Convolutional neural networks are paramount in image and signal processing including the relevant classification and training tasks alike and constitute for the majority of machine learning compute demand today.
PATRON: Exploring respiratory signal derived from non-contact face videos for face anti-spoofing
To achieve the best possible performance, our novel method, 𝑃𝐴𝑇𝑅𝑂𝑁 that is resPiration bAsed feaTuRes fOr 3D face mask aNti-spoofing is based on: i)different characteristics as that of rPPG methods; ii) appropriate selection of facial regions; iii) relevant feature selection, and iv) compact feature representation.
SWIS -- Shared Weight bIt Sparsity for Efficient Neural Network Acceleration
Quantization is spearheading the increase in performance and efficiency of neural network computing systems making headway into commodity hardware.
MOMBAT: Heart Rate Monitoring from Face Video using Pulse Modeling and Bayesian Tracking
We alleviate these issues by proposing a novel face video based HR monitoring method MOMBAT, that is, MOnitoring using Modeling and BAyesian Tracking.
CIIDefence: Defeating Adversarial Attacks by Fusing Class-Specific Image Inpainting and Image Denoising
This paper presents a novel approach for protecting deep neural networks from adversarial attacks, i. e., methods that add well-crafted imperceptible modifications to the original inputs such that they are incorrectly classified with high confidence.
Optimizing Multi-GPU Parallelization Strategies for Deep Learning Training
This work explores hybrid parallelization, where each data parallel worker is comprised of more than one device, across which the model dataflow graph (DFG) is split using MP.
