Okay, so we’ll get into actually using a neural network right now! The idea is to create what is called a “dictomizer”. A dictomizer can differentiate between two “classes” of things. For example, checking if something is “human” or “not human”. Or maybe checking if a book is “printed” or “hand written”. The examples I [...]
Modern artificial neurons have been derived from McCulloch-Pitts model, but with some changes. These changes allow us to create physical neural networks (using resistors, opamps, etc) relatively easily. Plus, these changes make the neurons much more versatile and can adapt to a wider range of applications. The changes I assume you’ve gone through the post [...]
The McCulloch-Pitts model was an extremely simple artificial neuron. The inputs could be either a zero or a one. And the output was a zero or a one. And each input could be either excitatory or inhibitory. Now the whole point was to sum the inputs. If an input is one, and is excitatory in [...]
Artificial neural networks are inspired from biological ones. So it makes sense to know a bit about biological neural networks as well. You brain is a neural network. One really really complex neural network. It has 1011 neurons. And each of these neurons is connected to approximately 104 other neurons. These interconnected neurons use electrical [...]
Today, computers are greatly evolved machines. They run at blindingly fast processor speeds of around 3 GHz. That too with multiple cores. They can do calculations, perform mathematical manipulations, forecast weather, guide missles with pin point accuracy. Something which humans simply cannot do at such high speeds. But there are tasks that humans can do [...]
My name is Utkarsh Sinha, and I'm an undergraduate student, pursuing B.E. Computer Science + M.Sc. Mathematics. Here, I help you understand ideas in Artificial Intelligence, using a not so techy and mathematical language. And in the process, learn more about Artificial Intelligence myself.
