Introduction to Deep Learning

Artificial intelligence is when machines can perform tasks that would normally require human intelligence. It includes machine learning, in which machines learn via experience and develop skills without the need for human intervention.

Deep learning is a subset of machine learning. DL techniques are inspired by the human brain, learn from enormous volumes of data. The deep learning algorithm would repeat a task, modifying it slightly each time to enhance the outcome, like how we learn from experience. Because neural networks have various (deep) layers that permit learning, we refer to it as deep learning.

Below are some of the applications of Deep Learning 
• Self Driving Cars.
• News Aggregation and Fraud News Detection.
• Natural Language Processing.
• Virtual Assistants.
• Entertainment.
• Visual Recognition.
• Fraud Detection.
• Healthcare.

Deep learning concept was introduced by Geoffrey Hinton in the 1980s. 

He did comparison of ML approaches to human brain. He created the idea of the term “neural network,” which refers to a deep learning algorithm that is arranged similarly to the way neurons in the brain are organized. Because the human brain is perhaps the most powerful computational engine.

Hinton structure called as an artificial neural network (ANN) (or artificial neural net for short) is as follows :

• Node layers are used in artificial neural networks.
• Each node is programmed to act in the same way as a brain neuron.
• The input layer is the initial layer of a neural network, then hidden layers, and lastly the output layer.
• Each node in the neural network conducts a calculation that is then passed on to nodes further down the network.

Neurons receive one or more input signals. These input signals can come from either the raw data set or from neurons positioned at a previous layer of the neural net. They perform some calculations. They send some output signals to neurons deeper in the neural network.

Let’s look at the fundamental differences between Machine learning and Deep Learning

Machine Learning :

• Machine learning does not require a large amount of data to function; nevertheless, it can function with a smaller amount of data.
• Machine learning algorithm takes less time to train the model than deep learning, but it takes a long-time duration to test the model.
• Machine learning models do not need much amount of data, so they can work on low-end machines.
• Data in a structured format is required by most machine learning models.

Deep Learning :

• Deep learning algorithms rely heavily on a huge number of data, we must feed a significant amount of data to achieve effective results.
• Deep Learning takes a long execution time to train the model, but less time to test the model.
• Deep learning model needs a huge amount of data to work efficiently, so they need GPU’s and hence the high-end machine.
• Deep Learning models can work with structured and unstructured data both as they rely on the layers of the Artificial neural network.

To summarize, deep learning is machine learning with greater capabilities and a different approach to problem solving. And deciding which one to use to tackle a particular problem is dependent on the amount of data and the problem’s complexity.