EYE ON AI: Learn all about Artificial Intelligence by Ranveer Patel

Author:Ranveer Patel [Patel, Ranveer]
Language: eng
Format: azw3
Published: 2020-05-16T16:00:00+00:00

Bob’s parents spent countless hours teaching (supervised learning) him ABC’s and 123’s when he was young.

Bob’s has grown up and he can understand and recognize patterns on his own (unsupervised learning). He has no issues telling digit ‘2’ written 1000 different ways.

To train an Artificial Neural Network or ANN, a scientist/engineer provides a known input and expected output, and the scientist runs the iterative process where neural network is given an input and is self-adjusting the weights and unit step function until it is providing the desired output. So, if the scientist is training the neural network to recognize handwritten digits, it would provide a dataset of digit 2 written by 1000 or 10,000 people and set expected output of the neural network to be digit ‘2’. Once the neural network is trained on the 1000 or 10,000 images, when it encounters handwritten digit ‘2’ it will produce a computer readable digit ‘ 2’ as an output. This is also called classification.

The process of training the neural network model uses positive and negative reinforcement very similar to how you would train a dog. An example of positive reinforcement would be when the dog performs a trick that you ask it to perform you give him a small treat. Similarly, negative reinforcement would imply the dog gets timeout when it does something silly. Once the neural network is fully trained, and is providing the desired result, it is saved as a neural network model.

The neural network model can now be presented with test or real data and the neural network is able to classify the data based on the training.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.