Introduction to Deep Learning

Introduction to Deep Learning:

• Deep Learning is a family of machine learning methods based on artificial neural networks.
• Machine learning is defined as a discipline within AI that teaches computers how to make predictions based on data.
• Computer scientists have found a way to mimic the human brain inside machines: Artificial neural networks. The goal of using these neural networks is to approach and solve general and complex problems in a similar way to how a human brain does.
• The main difference between ML & DL is that in DL there is no pre-defined framework and all we have is a Deep Neural Network (DNN) with multiple layers.
• In the case of non-DL methods there are certain frameworks that we tried to fit on the data to explain the patterns that we are seeing.

Artificial Neural Networks:

• Artificial neural networks (ANNs) are computational models inspired by the structure and function of biological neural networks in the human brain.
• ANNs consist of interconnected nodes, called artificial neurons or nodes, which are organized in layers.
• Each neuron receives input signals, performs a computation, and produces an output signal that is passed to the next layer of neurons.
• The connections between neurons have associated weights that determine the strength of the signal transmitted from one neuron to another.
• ANNs are trained using a process called backpropagation, where the weights of the connections are adjusted based on the error between the predicted output and the desired output.
• This training process allows ANNs to learn from data and make predictions or decisions based on that learning.

Deep Neural Network:

• It’s an artificial construct designed to mimic how the human brain works. The way to think about it is that a DNN will learn about your data set just as a baby will learn a language or how to differentiate between objects.
• It has a brain, it has no predefined network that we put in there and simply by walking around and interacting with humans, it automatically and slowly learns how to talk, how to walk, and how to do other things.
• The drawback with DL is that it requires a lot of data, much more data than other algorithms. It might require thousands, hundreds of thousands, or even millions of examples before it can come up with those features and truly learn.

Contents:

1. Building Neural Networks
2. How Neural Networks Work
3. Deep Learning Use Cases