Survey on Energy-Efficient Deep Neural Networks for Computer Vision

2022 ◽  
pp. 25-52
Author(s):  
Abhinav Goel ◽  
Caleb Tung ◽  
Xiao Hu ◽  
Haobo Wang ◽  
Yung-Hsiang Lu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Energy Efficient ◽  
Deep Neural Networks

scholarly journals Off-the-shelf deep learning is not enough, and requires parsimony, Bayesianity, and causality

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Rama K. Vasudevan ◽  
Maxim Ziatdinov ◽  
Lukas Vlcek ◽  
Sergei V. Kalinin
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Deep Learning ◽  
Bayesian Methods ◽  
Deep Neural Networks ◽  
Applied Research ◽  
Modern Science ◽  
Generative Models ◽  
Knowledge Development ◽  
Physical Constraints

AbstractDeep neural networks (‘deep learning’) have emerged as a technology of choice to tackle problems in speech recognition, computer vision, finance, etc. However, adoption of deep learning in physical domains brings substantial challenges stemming from the correlative nature of deep learning methods compared to the causal, hypothesis driven nature of modern science. We argue that the broad adoption of Bayesian methods incorporating prior knowledge, development of solutions with incorporated physical constraints and parsimonious structural descriptors and generative models, and ultimately adoption of causal models, offers a path forward for fundamental and applied research.

Compensated-DNN: Energy Efficient Low-Precision Deep Neural Networks by Compensating Quantization Errors

2018 ◽  
Author(s):  
Shubham Jain ◽  
Swagath Venkataramani ◽  
Vijayalakshmi Srinivasan ◽  
Jungwook Choi ◽  
Pierce Chuang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Energy Efficient ◽  
Deep Neural Networks

Vesti: Energy-Efficient In-Memory Computing Accelerator for Deep Neural Networks

2020 ◽  
Vol 28 (1) ◽  
pp. 48-61 ◽  
Author(s):  
Shihui Yin ◽  
Zhewei Jiang ◽  
Minkyu Kim ◽  
Tushar Gupta ◽  
Mingoo Seok ◽  
...  
Keyword(s):  
Neural Networks ◽  
Energy Efficient ◽  
Deep Neural Networks

X-DNNs: Systematic Cross-Layer Approximations for Energy-Efficient Deep Neural Networks

2018 ◽  
Vol 14 (4) ◽  
pp. 520-534 ◽  
Author(s):  
Muhammad Abdullah Hanif ◽  
Alberto Marchisio ◽  
Tabasher Arif ◽  
Rehan Hafiz ◽  
Semeen Rehman ◽  
...  
Keyword(s):  
Neural Networks ◽  
Energy Efficient ◽  
Deep Neural Networks ◽  
Cross Layer

scholarly journals COSMO: Computing with Stochastic Numbers in Memory

2022 ◽  
Vol 18 (2) ◽  
pp. 1-25
Author(s):  
Saransh Gupta ◽  
Mohsen Imani ◽  
Joonseop Sim ◽  
Andrew Huang ◽  
Fan Wu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Energy Efficient ◽  
Deep Neural Networks ◽  
Parallel Architecture ◽  
Low Energy ◽  
Stochastic Computing ◽  
Wide Range ◽  
Low Energy Consumption ◽  
Sc Addition

Stochastic computing (SC) reduces the complexity of computation by representing numbers with long streams of independent bits. However, increasing performance in SC comes with either an increase in area or a loss in accuracy. Processing in memory (PIM) computes data in-place while having high memory density and supporting bit-parallel operations with low energy consumption. In this article, we propose COSMO, an architecture for co mputing with s tochastic numbers in me mo ry, which enables SC in memory. The proposed architecture is general and can be used for a wide range of applications. It is a highly dense and parallel architecture that supports most SC encodings and operations in memory. It maximizes the performance and energy efficiency of SC by introducing several innovations: (i) in-memory parallel stochastic number generation, (ii) efficient implication-based logic in memory, (iii) novel memory bit line segmenting, (iv) a new memory-compatible SC addition operation, and (v) enabling flexible block allocation. To show the generality and efficiency of our stochastic architecture, we implement image processing, deep neural networks (DNNs), and hyperdimensional (HD) computing on the proposed hardware. Our evaluations show that running DNN inference on COSMO is 141× faster and 80× more energy efficient as compared to GPU.

scholarly journals Technical note: AI-Track-tive: automated fission track recognition using computer vision (Artificial Intelligence)

2020 ◽  
Author(s):  
Simon Nachtergaele ◽  
Johan De Grave
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Neural Networks ◽  
Fission Track ◽  
Detection Algorithm ◽  
Technical Note ◽  
Success Rates ◽  
Automatic Counting ◽  
First Time

Abstract. Artificial intelligence techniques such as deep neural networks and computer vision are developed for fission track recognition and included in a computer program for the first time. These deep neural networks use the Yolov3 object detection algorithm, which is currently one of the most powerful and fastest object recognition algorithms. These deep neural networks can be used in new software called AI-Track-tive. The developed program successfully finds most of the fission tracks in the microscope images, however, the user still needs to supervise the automatic counting. The success rates of the automatic recognition range from 70 % to 100 % depending on the areal track densities in apatite and (muscovite) external detector. The success rate generally decreases for images with high areal track densities, because overlapping tracks are less easily recognizable for computer vision techniques.

scholarly journals Avaliação do Processo para Embarcar uma Rede Neural Baseada em YOLO Utilizando um Acelerador de Hardware Dedicado

2020 ◽  
Author(s):  
Isabel Costa ◽  
Elias Silva Jr ◽  
Antônio Rodrigues ◽  
Leandro Angeloni ◽  
Edmilson Dias
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Object Detection ◽  
Power Distribution ◽  
Deep Neural Networks ◽  
Aerial Images ◽  
Great Progress ◽  
Operational Networks

Object Detection is a challenging task in computer vision, but Deep Neural Networks (DNN) have made great progress in this area. This work presents the process and the results obtained in the attempts to embed a YOLO V3 model in a Neural Compute Engine, the Movidius Stick. Experiments were carried out with a Tensorflow model that is converted to Movidius (using OpenVINO) including an evaluation of the Movidius stick connected to a Raspberry Pi3. The application uses aerial images of power distribution towers captured by a drone. Although there are some fully operational networks for Neural Compute Engines, there are some difficulties in porting new networks to the platform, with gains in performance, but with losses in accuracy.

scholarly journals Vision beyond Pixels: Visual Reasoning via Blocksworld Abstractions

2019 ◽  
Author(s):  
Tejas Gokhale
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Cognitive Psychology ◽  
Visual Perception ◽  
Deep Neural Networks ◽  
Natural Images ◽  
Modular Approach ◽  
Reasoning Task ◽  
Two Stages ◽  
Event Sequencing

Deep neural networks trained in an end-to-end fashion have brought about exceptional advances in computer vision, especially in computational perception. We go beyond perception and seek to enable vision modules to reason about perceived visual entities such as scenes, objects and actions. We introduce a challenging visual reasoning task, Image-Based Event Sequencing (IES) and compile the first IES dataset, Blocksworld Image Reasoning Dataset (BIRD). Motivated by the blocksworld concept, we propose a modular approach supported by literature in cognitive psychology and children's development. We decompose the problem into two stages - visual perception and event sequencing, and show that our approach can be extended to natural images without re-training.

Sign in / Sign up

Export Citation Format

Share Document