I've always been interested in Neural Networks (ever since I first found out about them around 10 years ago). However, I never got a chance to learn about them or write one of my own; this is something I've wanted to do for some time. I got the opportunity this semester when my professor in my advanced data-structures class told us that we could pick any topic we liked, for a semester project. I thought that this would be the perfect time for me to learn about neural networks and create one of my own.
The end result was Akṣi, a neural network that recognizes hand-written digits. I've hosted it using Google's App Engine. Please check it out!
1 thought on “Akṣi: Handwritten-digit-recognizing neural-network”
I am Raghul Murugesan. I am from India. I am currently pursing masters in Computer Engineering from University of Houston. I saw ur presentation on Handwritten Digit-Recognizing Neural-Network on youtube and I am try to do the same in java.
I am sorry to bother you, but I am have a question about the ur neural network. My question is
Do we need to save every adjusted weights after training each training sample (say a hand written digit eg 0 ). if so then we will have very large no of weights?
I am trying my best to understand how u have trained this but i am not able to fully get it. I have done a fare amount of research on this, can u please help me?