1) Exam-Oriented Simplified Notes: Artificial Intelligence & Machine Learning

I. Artificial Intelligence (AI) Fundamentals

  • Definition: AI is the science of making machines that can think like humans, enabling them to learn from experience, adapt, and perform human-like tasks. It involves building smart machines with the intelligence of machines or software.
  • Purpose: Making a Machine intelligent.
  • The Term AI: Coined by John McCarthy.
    • Year Coined: 1956.
    • Conference: The term was first coined in 1956 at the Dartmouth Conference.
  • First Demonstration: The first demonstration of an AI program ran at Carnegie Mellon University.
  • Evolution Sequence: 1) Birth of AI $\rightarrow$ 2) Neural Network $\rightarrow$ 3) Machine Learning $\rightarrow$ 4) Deep Learning.

II. AI Hierarchy and Branches

Branches of AI (6 Total):

  1. Machine Learning (ML)
  2. Deep Learning (DL)
  3. Natural Language Processing (NLP)
  4. Robotics
  5. Expert Systems
  6. Fuzzy Logic

Note: Virtual Reality (VR) is NOT a subfield/branch of AI.

Types of AI (4 Total):

  1. Reactive Machines AI
  2. Limited Memory AI
  3. Theory Of Mind AI
  4. Self-aware AI

III. Machine Learning (ML)

  • Definition: ML is a subset of AI. It focuses on building applications that can learn from data to improve accuracy over time without human intervention.
  • Key Focus: Use of data and algorithms.
  • Founders:
    • Term 'Machine Learning' coined in 1959 by Arthur Samuel (IBM).
    • Father/Founder of Machine Learning: Geoffrey Everest Hinton.
  • Data Mining Connection: Application of machine learning methods to large databases is called Data Mining.

IV. Types of Machine Learning (ML)

Type Key Characteristics Examples / Objective
1. Supervised Learning Requires supervision and labeled training data. Requires input and output attributes. Objective is to map input (x) to output (y). Examples: Risk Assessment, Fraud Detection, Spam filtering, Classifying positive/negative reviews.
2. Unsupervised Learning No supervision needed; uses unlabeled data. Objective is to discover hidden patterns or data groupings. Examples: Neural Networks, Anomaly detection.
3. Reinforcement Learning Works on a feedback-based process (Hitting & Trail method). Autonomous, self-teaching system. Applications: Real-Time decisions, Game AI, Skill acquisition, Robot Navigation.

V. Deep Learning (DL)

  • Definition: DL is an advance form of AI and a subset of Machine Learning. It teaches computers to process data in a way inspired by the human brain.
  • Structure: DL models are neural networks with three or more layers.
    • Input layer: Data enters.
    • Hidden layers: Process and transport data.
    • Output layer: Final result or prediction is made.
  • Examples: Self-driving cars, Facial recognition, Medical science, Speech recognition, Digital assistants, Fraud detection.

VI. Key AI Languages, Robotics, and Chatbots

Programming Languages for AI:

  • Commonly Used: Python (often considered the best choice), LISP (LISt Processing - historically significant and the first AI programming language called IPL), PROLOG (Programming in Logic), Java, JavaScript, C++, Julia, Haskell, Scala, R.
  • LISP Creator: John McCarthy.
  • Not Commonly Used (Tested): Perl.

Robotics History:

  • Robot Arm: A robot’s "Arm" is called a Manipulator (also Actuator/Effector are related parts).
  • First Robot: Introduced in 1960 to the General Motor’s Assembly Line.

Chatbots and Virtual Assistants Chronology:

Product / Chatbot Developer / Company Year/Details
First Chatbot: Eliza N/A Introduced in 1961.
Siri (Virtual Assistant) Apple Year: 2011.
Alexa (Virtual Assistant) Amazon Year: 2014.
Cortana (Virtual Assistant) Microsoft Year: 2014 (End Services: March 31, 2021).
Bixby (Virtual Assistant) Samsung Year: 2017.
ChatGPT (AI Chatbot) OpenAI (San Francisco startup) Initially released November 30, 2022. The acronym GPT stands for Generative Pre-trained Transformer. Trained using RLHF (Reinforcement Learning from Human Feedback). Latest version mentioned is ChatGPT 4o. It is a Large Language Model (LLM).
Bard / Gemini Google Rivals ChatGPT.