Past few months I have been delving into the AI, ML and Deep Learning and related topics. My interest got triggered after coming across a session on Fast.ai that is a free Deep Learning framework from Jeremy Howard. Here is the link to the online course.
Background
In my college days we had customary lab assignment and competition to build AI based Machine vs Machine game of checkers. This involved using AI game trees (Min Max trees) to look ahead and evaluate board positions and choosing the right moves that will lead to a favorable board position. Our team won the competition by beating the opponent team. We had plans to use machine learning to improve the performance but had to stop due the time constraints as this was just a lab assignment.
Current Status
Fast forward two decades, I am back into rediscovering the AI with new enhancements made possible due to the advent of Cloud Computing and the availability of cheaper GPUs. Now the super computing is accessible to general public. The research in the AI domain has also undergone tremendous improvements leading to lot of optimizations and specialized neural networks to solve specific problems.
Enthusiastic to know about the latest developments, I enrolled myself into the Machine Learning course by Andrew Ng at Coursera. This course was mostly theory with weekly assignments. This is a good foundation to start learning Machine Learning.
Deep Learning Presentation
Based on whatever knowledge I have gained, I decided to give a presentation in the Hyderabad Software Architects group. This turned out to be a great success which led me to plan for a presentation on the Deep Learning. It took a lot of effort to understand the various options available in building Deep Learning networks. Finally, I gave a presentation on Deep Learning. Walking Tree Tech was kind enough to provide the venue.
My presentation was telecast live on Facebook. The recording of which is available at here.
As part of the demo, I have trained a Convolutional Neural Network using Keras with the Microsoft CNTK as the back-end. I have used the Azure Deep Learning Virtual machine to do the training. This Virtual Machine comes with NVidia K80 GPU. Using the GPU for training speeds up the training time.
The slides for the Deep Learning session are here.
The session was a great success. The interactive discussions helped everyone. I am planning to give some more sessions on Deep Learning which will delve into different Deep Learning architectures.
To summarize my experience and continue my commitment to blog at least once a week I am writing this blog on the session.
Nice information Thanks for sharing nice article..