Activation Function: Key to Cloning from Human Learning to Deep Learning

Activation Function: Key to Cloning from Human Learning to Deep Learning

Pranit Gopaldas Shah MTech CE, BECE, MPM, FCSRC, Chief Research Scientist, TeerHub Technology Private Limited

Contact

Hiral Pranit Shah

Contact

Parul University

Activation Function: Key to Cloning from Human Learning to Deep Learning

Article Fingerprint

ReserarchID

1APUS

Activation Function: Key to Cloning from Human Learning to Deep Learning Banner

AI TAKEAWAY

Connecting with the Eternal Ground

Abstract

Maneuvering a steady on-road obstacle at high speed involves taking multiple decisions in split seconds. An inaccurate decision may result in crash. One of the key decision that needs to be taken is can the on-road steady obstacle be surpassed. The model learns to clone the drivers behavior of maneuvering a non-surpass-able obstacle and pass through a surpass-able obstacle. No data with labels of “surpass-able” and “non-surpass-able” was provided during training. We have development an array of test cases to verify the robustness of CNN models used in autonomous driving. Experimenting between activation functions and dropouts the model achieves an accuracy of 87.33% and run time of 4478 seconds with input of only 4881 images (training + testing). The model is trained for limited on-road steady obstacles. This paper provides a unique method to verify the robustness of CNN models for obstacle mitigation in autonomous vehicles.

References

32 Cites in Article

Reference Format

Ross Girshick,Jeff Donahue,Trevor Darrell,Jitendra Malik (2016). Region-Based Convolutional Networks for Accurate Object Detection and Segmentation.
J Redmon,S Divvala,R Girshick,A Farhadi (2016). You only look once: Unified, real-time object detection.
Mariusz Bojarski,Philipyeres,Krzyszt Annachoromanska,Bernhard Of Choromanski,Lawrence Firner,Urs Jackel,Muller (2017). Explaining how a deep neural network trained with end-to-end learning steers a car.
Ivan Bratko,Tanja Urbančič,Claude Sammut (1995). Behavioural Cloning: Phenomena, Results and Problems.
Saumya Kumaar,Navaneeth Krishnan,Sinchana Hegde,Pragadeesh Raja,Ravi Vishwanath (2019). Towards Behavioural Cloning for Autonomous Driving.
Mariusz Bojarski,Davide Testa,Dworakowski,Bernhard Daniel & Firner,Flepp,& Beat,Prasoon Goyal,Lawrence Jackel,Mathew Monfort,Urs Muller,Jiakai Zhang,Xin Zhang,Jake Zhao,Karol Zieba (2016). End to End Learning for Self-Driving Cars.
Alex Krizhevsky,Ilya Sutskever,Geoffrey Hinton Imagenet classi fication with deep convolutional neural networks.
Curran Associates,Inc (2012). Unknown Title.
(2004). Using net energy methodology for energy planning: tradeoffs of supply vs. end-use technologies. Volume II. Final report. [New England].
Sara Moussawi,Joseph Mertz,Jeria Quesenberry,Xiaoying Tu,Julia Poepping,Larry Heimann,Raja Sooriamurthi,Divakaran Liginlal,Christopher Kowalsky,Martin Barrett,Gabriela Gongora-Svartzman,Oscar Veliz,Laura Pottmeyer,Michael Melville (1989). Building Future Information Systems Leaders: The Crucial Role of Problem Scoping in Service-Learning Experiences.
Kwang An,Sung Lee,Seung-Ki & Ryu,Dongmahn Seo (2018). Detecting a pothole using deep convolutional neural network models for an adaptive shock observing in a vehicle driving.
Sumit Srivastava,Ayush Sharma,Harsh Balot (2018). Analysis and Improvements on Current Pothole Detection Techniques.
Yue Wang,Eam Teoh,Dinggang Shen (2004). Lane detection and tracking using B-Snake.
A Assidiq,O Khalifa,M Islam,S Khan (2008). Real time lane detection for autonomous vehicles.
Y Li,A Iqbal,N Gans (2014). Multiple lane boundary detection using a combination of low-level image features.
Jia He,Hui Rong,Jinfeng Gong,Wei Huang (2010). A Lane Detection Method for Lane Departure Warning System.
Zhixiong Nan,Ping Wei,Linhai Xu,Nanning Zheng (2016). Efficient Lane Boundary Detection with Spatial-Temporal Knowledge Filtering.
E,Buza Omanovic,A Huseinovic (2013). Pothole Detection with Image Processing and Spectral Clustering.
Kelvin Wang (2004). Challenges and Feasibility for Comprehensive Automated Survey of Pavement Conditions.
Z Hou,K Wang,W Gong (2007). Experimentation of 3D pavement imaging through stereovision.
D Joubert,A Tyatyantsi,J Mphahlehle,V Manchidi (2011). 2012 5th Robotics and Mechatronics Conference of South Africa.
I Moazzam,K Kamal,S Mathavan,S Usman,M Rahman (2013). Metrology and visualization of potholes using the microsoft kinect sensor.
Pranit Shah,Krishna Pandya,Shah,& Harsh,Jay Gandhi (2019). Survey on Vision based Hand Gesture Recognition.
Q Li,M Yao,Yao,B Xu (2009). A real-time 3D Scanning System for pavement distortion inspection, measurement science and technology.
Umang Bhatt,Mani,& Shouvik,Xi,J Edgar & Kolter (2017). Intelligent Pothole Detection and Road Cond0ition Assessment.
B Huval,T Wang,S Tandon,J Kiske,W Song,J Pazhayampallil,M Andriluka,T Rajpurkar,R Migimatsu,Cheng-Yue (2015). An empirical evaluation of deep learning on highway driving.
C Chen,A Seff,A Kornhauser,J Xiao (2015). Deepdriving: Learning affordance for direct perception in autonomous driving.
Alexander Binder,Sebastian Bach,Gregoire Montavon,Klaus-Robert Müller,Wojciech Samek (2016). Layer-Wise Relevance Propagation for Deep Neural Network Architectures.
Zhong-Qiu Zhao,Peng Zheng,Shou-Tao Xu,Xindong Wu (2019). Object Detection With Deep Learning: A Review.
Wenguan Wang,Qiuxia Lai,Huazhu Fu,Jianbing Shen,Haibin Ling,Ruigang Yang (2019). Salient Object Detection in the Deep Learning Era: An In-Depth Survey.
Antonio Loquercio,Ana Maqueda,Carlos Del-Blanco,Davide Scaramuzza (2018). DroNet: Learning to Fly by Driving.
Pranit Shah,Krishna Pandya,Harsh Shah,Jay Gandhi (2019). Survey on Vision based Hand Gesture Recognition.

Download References

Funding

No external funding was declared for this work.

Conflict of Interest

The authors declare no conflict of interest.

Ethical Approval

No ethics committee approval was required for this article type.

Data Availability

Not applicable for this article.

How to Cite This Article

Pranit Gopaldas Shah. 2020. \u201cActivation Function: Key to Cloning from Human Learning to Deep Learning\u201d. Global Journal of Computer Science and Technology - D: Neural & AI GJCST-D Volume 20 (GJCST Volume 20 Issue D1).

More Citation Formats

Select Citation Style:

Download Citation

GJCST Volume 20 Issue D1

Explore Journals Explore Volume Read This Issue

Journal Specifications

Crossref Journal DOI 10.17406/gjcst

Print ISSN 0975-4350

e-ISSN 0975-4172

Keywords

Not Found

Classification

GJCST-D Classification I.2.6

Submission ReceivedDecember 16, 2019
Peer Review Double Blind
Handling Editor
Accepted January 5, 2020
Published January 15, 2020

Version of record

v1.2

Issue date

June 8, 2020

Language

Experiance in AR

Explore published articles in an immersive Augmented Reality environment. Our platform converts research papers into interactive 3D books, allowing readers to view and interact with content using AR and VR compatible devices.

View in VR

Read in 3D

Your published article is automatically converted into a realistic 3D book. Flip through pages and read research papers in a more engaging and interactive format.

View in 3D

Article Matrices

Total Views: 4475

Total Downloads: 1113

2026 Trends

Our website is actively being updated, and changes may occur frequently. Please clear your browser cache if needed. For feedback or error reporting, please email [email protected]