Conditional Classification: A Solution for Computational Energy Reduction

Deep convolutional neural networks have shown high efficiency in computer visions and other applications. However, with the increase in the depth of the networks, the computational complexity is growing exponentially. In this paper, we propose a novel solution to reduce the computational complexity of convolutional neural network models used for many class image classification. Our proposed technique breaks the classification task into two steps: 1) coarse-grain classification, in which the input samples are classified among a set of hyper-classes, 2) fine-grain classification, in which the final labels are predicted among those hyper-classes detected at the first step. We illustrate that our proposed classifier can reach the level of accuracy reported by the best in class classification models with less computational complexity (Flop Count) by only activating parts of the model that are needed for the image classification.

[1]  Tianshi Chen,et al.  ShiDianNao: Shifting vision processing closer to the sensor , 2015, 2015 ACM/IEEE 42nd Annual International Symposium on Computer Architecture (ISCA).

[2]  Nitish Srivastava,et al.  Discriminative Transfer Learning with Tree-based Priors , 2013, NIPS.

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Avesta Sasan,et al.  ICNN: An iterative implementation of convolutional neural networks to enable energy and computational complexity aware dynamic approximation , 2018, 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[5]  Avesta Sasan,et al.  NESTA: Hamming Weight Compression-Based Neural Proc. EngineAli Mirzaeian , 2019, 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC).

[6]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[7]  Kaushik Roy,et al.  Conditional Deep Learning for energy-efficient and enhanced pattern recognition , 2015, 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[8]  Joel Emer,et al.  Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks , 2016, CARN.

[9]  Avesta Sasan,et al.  2SMaRT: A Two-Stage Machine Learning-Based Approach for Run-Time Specialized Hardware-Assisted Malware Detection , 2019, 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[10]  Kia Bazargan,et al.  HBUCNNA: Hybrid Binary-Unary Convolutional Neural Network Accelerator , 2020, 2020 IEEE International Symposium on Circuits and Systems (ISCAS).

[11]  Ohad Shamir,et al.  Probabilistic Label Trees for Efficient Large Scale Image Classification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  James H. Jones,et al.  Deep Contextualized Word Embedding for Text-based Online User Profiling to Detect Social Bots on Twitter , 2020, 2020 International Conference on Data Mining Workshops (ICDMW).

[13]  Daniel J. Sorin,et al.  Bayesian Optimization for Efficient Accelerator Synthesis , 2020, ACM Trans. Archit. Code Optim..

[14]  Avesta Sasan,et al.  LASCA: Learning Assisted Side Channel Delay Analysis for Hardware Trojan Detection , 2020, 2020 21st International Symposium on Quality Electronic Design (ISQED).

[15]  Avesta Sasan,et al.  Learning Assisted Side Channel Delay Test for Detection of Recycled ICs , 2020, 2021 26th Asia and South Pacific Design Automation Conference (ASP-DAC).

[16]  Hassan Ghasemzadeh,et al.  Design Space Exploration for Hardware Acceleration of Machine Learning Applications in MapReduce , 2018, 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM).

[17]  H. T. Kung,et al.  BranchyNet: Fast inference via early exiting from deep neural networks , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[18]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[19]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[20]  Jia Wang,et al.  DaDianNao: A Machine-Learning Supercomputer , 2014, 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture.

[21]  Samy Bengio,et al.  Large-Scale Object Classification Using Label Relation Graphs , 2014, ECCV.

[22]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[23]  Yuxin Peng,et al.  Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification , 2014, ACM Multimedia.

[24]  Robinson Piramuthu,et al.  HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  Avesta Sasan,et al.  TCD-NPE: A Re-configurable and Efficient Neural Processing Engine, Powered by Novel Temporal-Carry-deferring MACs , 2019, 2019 International Conference on ReConFigurable Computing and FPGAs (ReConFig).

[26]  James H. Jones,et al.  Using BERT to Extract Topic-Independent Sentiment Features for Social Media Bot Detection , 2020, 2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON).

[27]  Houman Homayoun,et al.  NNgSAT: Neural Network guided SAT Attack on Logic Locked Complex Structures , 2020, 2020 IEEE/ACM International Conference On Computer Aided Design (ICCAD).

[28]  Ninghui Sun,et al.  DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning , 2014, ASPLOS.