Sites Recommended


Online Learning Platforms

YouTube Channels/Playlists

 

Just for fun

Popular posts from this blog

Valentine's Day Card Using Python

Image
Love is in the air, what better way to wish your loved ones, then to write a code which draws a unique Valentine's Day Card especially for them. The card imports turtle to draw hearts at random positions on the canvas: You can get the code from: github
Read more

Brief Profile

Image
Amita Kapoor, is Associate Professor in the Department of Electronics, SRCASW, University of Delhi and has been actively teaching neural networks and artificial intelligence for the last 20 years. She completed her masters in Electronics in 1996 and PhD in 2011, during PhD she was awarded prestigious DAAD fellowship to pursue a part of her research work in Karlsruhe Institute of Technology, Karlsruhe, Germany. She was awarded best Presentation Award at the Photonics 2008 international conference. She is an active member of ACM, AAAI, IEEE, and INNS. She has co-authored two books. She has more than 40 publications in international journals and conferences. Her present research areas include ML, AI, Deep Reinforcement Learning and Robotics.
Read more

Deep Blue: A review

Image
Image Source: https://upload.wikimedia.org/wikipedia/commons/d/dc/Kasparov-29.jpg Paper: Deep Blue Authors: Murray Campbell, A Joseph Hoane Jr, feng-hsiung Hsu Introduction: Deep Blue was the chess machine (it is a powerful combination of hardware and software) developed by IBM. The machine became important in the field of AI because it was able to defeat the then World class Chess champion Garry Kasparov in the year 1997. This paper gives insight into the impressive hardware & software of Deep Blue. Key Points: Deep Blue learned from the experience of its predecessors ChipTest, Deep Thought, Deep Thought II and Deep Blue-I matches with human players. The major changes in the Deep Blue architecture were: Hardware Implemented Evaluation function: It's chess chip had a redesigned evaluation function based on over 8000 features. Since the evaluation function was implemented in hardware it offered constant execution time, but it also limited future feature additions. A majority of
Read more