Vijay Krishna's Notes http://vijaykrishna.posterous.com Most of my notes as a student of computer software and everything around it. posterous.com Fri, 28 Jan 2011 17:31:57 -0800 The Curious Case of Artificial Intelligence http://vijaykrishna.posterous.com/the-curious-case-of-artificial-intelligence http://vijaykrishna.posterous.com/the-curious-case-of-artificial-intelligence
Did you know that the first Matrix was designed to be a perfect human world? Where no one suffered, where everyone would be happy. It was a disaster. No one would accept the program, entire crops were lost. Some belived that we lacked the programming language to describe your perfect world...But I belive, that as a species, human beings define their reality though misery and suffering. - Agent Smith, The Matrix
This is probably the best way to define the human case. Infact, it is the best way to define the case of any sentient species. It is not our advances that define us, but our failures and imperfections. Today, my friend and i were having a very animated discussion on Artificial Intelligence at office. He spoke of AI agents and fuzzy logic and i was going on and on about the powers and shortcomings of the Artificial Neural Networks. All that talk led us to how technology and science has advanced to some very brilliant leads in this vast and illusive field, which encompasses Computational Theory, Biology, The study of the Brain, Psychology and Mathematics. However, very soon we started talking about what is yet to be done and we soon came to a common conclusion: there is no point in understanding and studying artificial intelligence, if the final aim of the subject is to emulate human/animal thinking. Why? Simply because of the fact that human thinking is about how we make mistakes and recover from them, not how brilliant we are at coming up with the best algorithms and solutions. You ought to study Natural Stupidity instead of Artificial Intelligence to really get a grasp of how human beings think. But then, is that really the true purpose of the subject. I think not. I think the crux of Artificial Intelligence is to develop some very superior methods of evaluating tough and computationally difficult problems. It is more about taking the efficiency and speed of a machine, and the computational agility of a natural brain i.e. the best of both worlds. While we have already understood and mastered the way of the machine and its efficiency and speed, we are yet to tackle the more complex issue of the brain. It is due to this exact situation, that the study or probably the exploration of the brain has been associated very vehemently with the study of AI. Many do not realize that it is not the central focus of the subject. For had it been that way, then every AI course would require a minor prerequisite course in Biology. Computer Scientists have always first tried to see if they could introduce the agility of a natural brain into their algorithms. They probably never wanted to even look at the brain beyond a point. It so happens that boolean algebra has its limitations. Or atleast we do in getting a complete grasp of the matter. Let me assure you this, the day the scientists have found a means to do what i just mentioned, a significant population of the world will loose interest in understanding the brain. I have always believed, that the day we can define a "smile" in terms of mathematical equations, we have shut the case of AI. Maybe that day, the difference between our brain and the best known algorithm would be close to nothing. But then the question remains, who will have to shift to bridge the gap? Will we finally unlock the secret to the brain and emotions as they exist today? Or will we have changed so much, in our quest for the answers, that our own thinking and emotions would become more machine like? Here is a random thought: if we were to unlock the secrets of the brain, would we not have developed mentally in doing so, and thus there would be so much more to learn about our newly developed aspects of our brain? So isn't it really a chase? One which we cannot win? And thus, does it not make sense to just come out with the superior algorithms instead of going whole hog on the mysteries of the mind? Food for thought.

Permalink | Leave a comment  »

]]>
http://files.posterous.com/user_profile_pics/1369599/pic.jpeg http://posterous.com/users/hcGXxsTkwP6SS Vijay Krishna Palepu vpalepu Vijay Krishna Palepu
Sun, 09 Jan 2011 16:33:02 -0800 Public Key Cryptography using ANNs http://vijaykrishna.posterous.com/public-key-cryptography-using-anns http://vijaykrishna.posterous.com/public-key-cryptography-using-anns Well, i took this post as a chance to show some of my undergraduate work i did. This was a part of my curriculum and it was one of the First things i really really like working on. But before i give you the link, let me brief you on what the whole thing was all about. ANNs or Artificial Neural Networks are an attempt to capture the neural nets of sentient beings. Its final purpose in my opinion is to model the Human neural network and finally the Human Brain leading to a better understanding of how things work. What they are has been given in the presentation that is to follow. What they do is actually quite simple: they learn.They are a system of logical entities which try and develop logic by a process of learning just like any sentient being. It has a teacher which is likely to be a teaching algorithm or another neural network. The neural net basically tries to formulate results for a given problem. In doing so it attains a state which can be determined by the values held by all its underlying sub-entities. It then compares its final Output value or results with the actual results. Based on the difference between the two, it corrects its own internal state and tries to recompute the results. It does so on a different problem but of the same type. If you recall this is how we would practice our Math sums as well, back in school. It does so till it starts to get the right set of results again and again and then declares its then corresponding internal state as the correct solution or approach to solving problems of that category. Now, if you fast forward to your college days you will remember that mutual learning or learning by discussion was faster. The same applies to Neural networks as well. When learning takes place between two untrained neural networks, it is very fast and they achieve a state of Neural Synchronization in a very fast manner. In this state their internal states are the same and it is this information which is used as the public keys for the encryption and decryption of messages. Now, this is not a classical public key crypto-system with a public key and a private key. There is in essence only one key which is known to the two mutually learning networks, and no one else. Now here is the good part: between the two neural nets, one does do not even know the state of the other. The moment they start communicating the correct results they are convinced that they have a common internal state (or understanding and approach in human terms) for the problem. That is the beauty. And this whole process can actually take place over a public network without compromising any level of secrecy. Having said all that, there are issues and in overcoming those issue lies our challenge. One of the major issues is that it might get highly computationally demanding. Well, enough said. Here is the link to the presentation i made for the technical seminar: Click here. Hope you find it interesting. It was at a very basic level. And do be critical of this work. How else will i improve.

Permalink | Leave a comment  »

]]>
http://files.posterous.com/user_profile_pics/1369599/pic.jpeg http://posterous.com/users/hcGXxsTkwP6SS Vijay Krishna Palepu vpalepu Vijay Krishna Palepu