Introduction to Deep Learning�

Presented by: OLUSANYA JOY

Date: March 25^th 2025

​

​

Overview & Objectives�

• Objective: Understand the basic concepts and applications of deep learning.

​

• Topics:
• Definitions of AI, machine learning, and deep learning.
• A brief history of neural networks.
• Examples of deep learning applications in real life.

​

What Is Intelligence?

As an example, in the New English Dictionary of 1932, intelligence was defined as: ‘The exercise of understanding: intellectual power: acquired knowledge: quickness of intellect.

What is Artificial Intelligence?

​

• Definition: AI refers to machines that mimic human intelligence to perform tasks. (Artificial intelligence is a way of making computers think intelligently, in a manner similar to how humans think. )
• Examples: Virtual assistants (Siri, Google Assistant), self-driving cars, fraud detection.

​

Hierarchy Diagram of AI, ML, and DL

Machine Learning vs. Deep Learning�

• Machine Learning (ML): Uses algorithms to learn from data and make predictions.(Machine learning is a subset of AI , that allows computers to learn from data and make decisions or predictions.)

​

• Deep Learning (DL): A subset of ML that uses neural networks to automatically learn features.(Deep learning, is a subfield of machine learning dealing with algorithms based essentially on multi-layered artificial neural networks (ANN) that are inspired by the structure of the human brain)

​

Machine Learning (ML):

• Input: A car image is given as input.
• Feature Extraction: A human manually extracts features (e.g., shape, color, size).
• Classification: A decision tree or similar ML algorithm is used for classification.
• Output: The system classifies the object as either "CAR" or "NOT CAR.
• Key point: ML relies on manual feature extraction before classification.

​

​

​

Deep Learning (DL)

​

• Input: A car image is given as input.
• Feature Extraction + Classification: A neural network automatically extracts features and classifies the image in a single step.
• Output: The system classifies the object as either "CAR" or "NOT CAR.

​

Key point: DL eliminates the need for manual feature extraction and learns patterns directly from raw data using deep neural networks.

A Brief History of Neural Networks�

• 1950s: Perceptron – first artificial neuron.
• 1980s: Backpropagation algorithm.
• 2010s: Deep Learning boom – GPUs & Big Data.
• Present: AI models like ChatGPT, DALL·E, and autonomous systems.

https://www.youtube.com/watch?v=AA2ettRM6_Q

Real-Life Applications of Deep Learning�

• Healthcare: Disease diagnosis (e.g., detecting cancer from medical scans).
• Finance: Fraud detection and stock market predictions.
• Entertainment: Netflix & Spotify recommendations.
• Autonomous Systems: Self-driving cars, robotics.

​

Summary�

• Deep Learning is a powerful AI technique based on neural networks.
• It is used in various fields like healthcare, finance, and autonomous systems.
• Advancements in computation power (GPUs) have accelerated its progress

​

​

Questions