Understanding the concepts of neural networks using Python and Numpy.

Image for post

Photo by Hello I’m Nik 🎞 on Unsplash

“Our intelligence is what makes us human, and A.I. is an extension of that quality.” — Yann LeCun Professor, New York University

Introduction ☕

The brain has always been one of the wonders that we still try to understand. We have been curious about its functioning and complexity for a long time. With advancements in research and technology, we are able to understand it to some extent, but there is a long way to go! On the quest to understand more about the brain we were able to develop something that we today call — Artificial Intelligence.

We will be going from basics and covering all parts needed to understand neural networks in depth. This is part contains a brief introduction to neural networks, AI, and deep learning concepts.

Motivation 😇

Consider images of a handwritten digit of number ‘1’ that a young child is trying to learn. The child learns by looking at the images (for example, fig (a)) after viewing many times. Next time, even if we show the number ‘1’ in a different handwriting-style(for example, fig (b)), the child will recognize that it’s ‘1’. We don’t have to teach the child to learn every unique handwriting style in the world or all the cases even with a different position. The brain learns even though the specific values image pixels will be different from each other for the two images.

Image for post

(Same number but different pixel values)

The particular pixel intensities that our visual system receives, for each set of images shown here are different. But still, we don’t have any difficulties in recognizing them both on number ‘1’. For a variety of images, photographs, places, sounds… anything that we sense is not constrained to the exact set of examples.

What if we have to teach the same task to make computers recognize the images of digits? Computers are dumb, they don’t have such a complex system (yet). The obvious way would be to program. Then we would need to consider all cases of pixel values, and unique ways of handwriting, etc.

But, then we would have to consider every possible steps and all the minute details! Wouldn’t that be so difficult?

#deep-learning #machine-learning #artificial-intelligence #python #neural-networks

Neural Networks from Scratch (A brief Introduction for Beginners)
1.10 GEEK