5.7 Neural Networks and Deep Learning

Introduction

Neural networks and deep learning have some differences, but they are closely related. Both are subsets of Machine Learning (ML). The textbook explains that machine learning is a branch of artificial intelligence that teaches computers to learn from data inputs and experience like humans without direct programming.

Machine learning algorithms enable computers to train on data inputs and analyze it to produce accurate output. It recognizes patterns in large databases to build models to automate decision-making.

Definition

Neural Networks are simulations of the working of the human brain, based on the functioning of neurons. They are networks of neurons that receive and send information throughout the network to make predictions and solve complex problems in a human-like manner.

Deep Learning (DL) is an AI technology that uses deep neural networks (neural networks with multiple hidden layers) to enable computers to autonomously extract hidden patterns and features from huge amounts of data for making decisions.

In simple words: Neural networks are computing systems inspired by the human brain. Deep learning is a type of machine learning that uses deep neural networks with many layers.

Main Idea

The core idea is that neural networks and deep learning are inspired by the human brain. Just as the brain has billions of neurons connected by synapses, a neural network has artificial neurons connected by weights. By adjusting these weights, the network can learn patterns and make predictions.

• Neural networks are simulations of the working of the human brain.
• A neuron is a computational unit of a neural network.
• Neural networks have a layered approach: input layer, hidden layers, output layer.
• Deep learning uses deep neural networks with multiple hidden layers.
• Deep learning requires vast amounts of data, more training time, and high-performance computers with GPUs.