Fundamentals of Machine Learning and Deep Learning

Fundamentals of Machine Learning (ML) and Deep Learning (DL)

• Machine Learning

Machine Learning is branch of Artificial Intelligence and is popular way to perform AI tasks through various methods. Simply in ML, there is no need to instruct computers, data is given to the system and according to past experience and data, rules are made by computers and apply further to get required results.

In this ML domain model of Al are trained on learning how to create general rule for themselves to perform lookalike tasks by taking specific inputs and their desired possible outputs. ML required processed data with human intervention. 

Most important things to note that ML algorithms uses neural networks and their hidden layers to process to the final results but these layers  are less i-e 1 or more in ML model, which provides less refined output or results. Other things are that numerous ML algorithms do not respond better on unstructured data as well as can’t handle large amount of data. 

• Deep Learning

Deep learning is also lie in the domain of AI and Machine Learning. In simple words, DL is inspired by biological neurons and study of neural networks is called deep learning. DL is the study of doing ML with neural networks. 

Neural Networks made up of basic and fundamental mathematical functions like comparing two value, equations etc. One of popular first digital neuron in history is ReLU (rectified linear unit) that is mathematical max function to provide highest value by comparing two different number values. 

In the past, we used to call Deep learning "Neural Networks". But later, it became known as Deep Learning because people thought it was too hard to make networks that worked like real brain cells. Also, scientists had trouble getting money for AI research when they talked about "Neural Networks" because of all the hype around them. So they changed the name to Deep Learning. Also first neural network made by Marvin Minsky in 1960 but failed due to discussed hype.

Network : When two are more things interlink together in a specific sequence to provide results or output form a network. 

Neural Networks or DL are based on 3 things.

1. Computational power

2. Bulk of data ( i-e exabyte or petabyte)

3. New algorithms and neurons creation. 

In contrast to ML, neural networks or DL, there are multiple layers of hidden layers. These layers helps to train AI model capable for providing most refined result of tasks. Most amazing thing is that DL models accept any type data as input whether it is structured or unstructured data. Also neural network are efficient in processing enormous large amount of information or data. 

Neural Networks are consist of 3 layers.

1. Input layer - takes input image or texts etc.

2. Hidden layer - steps to refine computations.

3. Output layer - provide final results. 

All we have discussed above is normally related to Discriminative AI. It is a type of artificial intelligence that focuses on learning to distinguish between different categories or classes in data. 

Read more blogs from Abdullah:

Introduction to AI

Discriminative and Generative AI

Prompt Engineering 

Diffusion Model in AI