0% Complete
Home
/
14th International Conference on Computer and Knowledge Engineering
Towards Efficient Capsule Networks through Approximate Squash Function and Layer-wise Quantization
Authors :
Mohsen Raji
1
Kimia Soroush
2
Amir Ghazizadeh
3
1- Shiraz university
2- Shiraz university
3- Shiraz university
Keywords :
Capsule Networks،Accelerated Squash Function،Post-Training Quantization،Quantization optimization
Abstract :
Capsule networks (CapsNets) have emerged as a promising architecture for various machine learning tasks due to their ability to capture hierarchical relationships within data. However, this structure has computationally intensive operations, particularly in the squash function, which involves square root calculations. In addition, they consume a lot of memory due to the high number of parameters, which makes them difficult to deploy on resource-constrained devices. In this paper, we take advantages of approximate computing and quantization to improve the efficiency of CapsNets performance. An approximate squash function is proposed using on the Fast Inverse Square Root (FISR) algorithm to accelerate square root operations, offering a remarkable speedup of up to 4 times compared to conventional methods. Additionally, we propose a novel algorithm called Least Sensitive Layer First (LSLF) in order to reduce the memory consumption of CapsNets. LSLF prioritizes aggressive quantization of the most error-tolerant layers while moderately quantizing the least sensitive layers against quantization error. Our experimental results demonstrate the effectiveness LSLF in enhancing the efficiency and performance of CapsNets, paving the way for more scalable and resource-efficient deep learning systems.
Papers List
List of archived papers
Classification of Audio Streaming in Network Traffic Based on Machine Learning Methods
Mohammad Nikbakht - Mehdi Teimouri
Towards Study of Research Topics Evolution in Artificial Intelligence based on Topic Embedding
Seyyed Reza Taher Harikandeh - Sadegh Aliakbary - Soroush Taheri
AL-YOLO: Accurate and Lightweight Vehicle and Pedestrian Detector in Foggy Weather
Behdad Sadeghian Pour - Hamidreza Mohammadi Jozani - Shahriar Baradaran Shokouhi
Time Series Analysis by Bi-GRU for Forecasting Bitcoin Trends based on Sentiment Analysis
Fatemeh Saadatmand - Mohammad Ali Zare Chahoki
Lightweight Local Transformer for COVID-19 Detection Using Chest CT Scans
Hojat Asgarian Dehkordi - Hossein Kashiani - Amir Abbas Hamidi Imani - Shahriar Baradaran Shokouhi
ExaASC: A General Target-Based Stance Detection Corpus in Arabic Language
Mohammad Mehdi Jaziriyan - Ahmad Akbari - Hamed Karbasi
Designing a High Perfomance and High Profit P2P Energy Trading System Using a Consortium Blockchain Network
Poonia Taheri Makhsoos - Behnam Bahrak - Fattaneh Taghiyareh
Efficient Object Detection using Deep Reinforcement Learning and Capsule Networks
Sobhan Siamak - Eghbal Mansoori
TrackMine: Topic Tracking in Model Mining using Genetic Algorithm
Mohammad Sajad Kasaei - Mohammadreza Sharbaf - Afsaneh Fatemi - Bahman Zamani
Hate Sentiment Recognition System For Persian Language
Pegah Shams jey - Arash Hemmati - Ramin Toosi - Mohammad ali Akhaee
more
Samin Hamayesh - Version 42.2.1