John McCarthy is often called the Father of Artificial Intelligence.
In 1950 Alan Turing gave the idea of the Turing Test, asking whether machines can think like humans.
1955–1956: John McCarthy, Marvin Minsky, Nathaniel Rochester, and Claude Shannon started the Dartmouth AI project; this is known as the beginning of Artificial Intelligence. 2012: Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton made a deep-learning breakthrough with AlexNet, starting the modern AI revolution. 2017: Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan Gomez, Łukasz Kaiser, and Illia Polosukhin introduced the Transformer model, which became the base of modern chatbots. 2022: OpenAI released ChatGPT, which made AI popular worldwide. 2023-GPT-4 and 2024-GPT40
Current AI Developers / Leaders:Sam Altman founded OpenAI in 2015, Demis Hassabis founded Google DeepMind in 2010, Dario Amodei founded Anthropic/Claude in 2021, Elon Musk founded xAI in 2023, and Arthur Mensch founded Mistral AI in 2023.
Simple exam point:
Main ML categories are Supervised, Unsupervised, and Reinforcement Learning.
Techniques like CNN, RNN, GAN, KNN, SVM, Decision Tree are
methods/algorithms used inside AI and ML.
Classified headings make it much
easier to memorize.
1. Core AI Terms
Abbreviation
Full Form
Short Detail
Example
AI
Artificial
Intelligence
Machines that
perform human-like tasks.
ChatGPT, robots
ML
Machine Learning
AI that learns from
data.
Marks prediction
DL
Deep Learning
ML using many neural
network layers.
Self-driving cars
AGI
Artificial General
Intelligence
Human-level general
AI.
Future AI concept
XAI
Explainable AI
Explains AI
decisions.
Why loan was
rejected
2. Main Machine
Learning Categories
Abbreviation
Full Form
Short Detail
Example
SL
Supervised Learning
Learns from labeled
data.
Spam / not spam
UL
Unsupervised
Learning
Finds patterns
without labels.
Customer grouping
RL
Reinforcement
Learning
Learns by rewards
and punishments.
Game AI
SSL
Semi-Supervised
Learning
Uses small labeled +
large unlabeled data.
Image classification
Self-SL
Self-Supervised
Learning
Creates its own
labels from data.
BERT, GPT
pretraining
3. Common ML
Algorithms
Abbreviation
Full Form
Short Detail
Example
KNN
K-Nearest Neighbors
Classifies using
nearest examples.
Fruit classification
SVM
Support Vector
Machine
Finds best boundary
between classes.
Spam detection
DT
Decision Tree
Uses tree-like
rules.
Loan approval
RF
Random Forest
Uses many decision
trees.
Disease prediction
NB
Naive Bayes
Probability-based
classifier.
Email spam filter
LR
Linear Regression
Predicts continuous
numbers.
House price
LogR
Logistic Regression
Predicts yes/no
class.
Disease yes/no
K-Means
K-Means Clustering
Groups similar data.
Customer groups
DBSCAN
Density-Based
Spatial Clustering of Applications with Noise
Finds clusters and
outliers.
Fraud detection
4. Neural Network /
Deep Learning Models
Abbreviation
Full Form
Short Detail
Example
NN
Neural Network
Brain-like model
that learns patterns.
Handwriting
recognition
ANN
Artificial Neural
Network
Basic neural network
model.
Classification
DNN
Deep Neural Network
Neural network with
many layers.
Image recognition
CNN
Convolutional Neural
Network
Best for image data.
Face detection
RNN
Recurrent Neural
Network
Best for sequence
data.
Text prediction
LSTM
Long Short-Term
Memory
Advanced RNN for
long memory.
Translation
GRU
Gated Recurrent Unit
Simpler version of
LSTM.
Speech recognition
AE
Autoencoder
Learns compressed
representation.
Noise removal
VAE
Variational
Autoencoder
Generates new data
using encoding.
Image generation
5. Generative AI
Models
Abbreviation
Full Form
Short Detail
Example
GAN
Generative
Adversarial Network
Generator creates
fake data, Discriminator checks it.
AI-generated faces
GPT
Generative
Pre-trained Transformer
Generates human-like
text.
ChatGPT
LLM
Large Language Model
Big model trained on
huge text data.
ChatGPT, Gemini
RAG
Retrieval-Augmented
Generation
AI answers using
retrieved documents.
PDF chatbot
VAE
Variational
Autoencoder
Generates new data
from learned patterns.
Image generation
6. NLP / Text AI
Techniques
Abbreviation
Full Form
Short Detail
Example
NLP
Natural Language
Processing
AI for human
language.
Chatbots
BERT
Bidirectional
Encoder Representations from Transformers
Understands text
from both directions.
Question answering
NER
Named Entity
Recognition
Finds names, places,
dates, etc.
“Ali lives in
Lahore”
POS
Part of Speech
Tagging
Identifies noun,
verb, adjective, etc.
Grammar analysis
BoW
Bag of Words
Represents text by
word count.
Text classification
TF-IDF
Term
Frequency–Inverse Document Frequency
Finds important
words in text.
Search engines
HMM
Hidden Markov Model
Used for sequence
prediction.
Speech recognition
CRF
Conditional Random
Field
Used for sequence
labeling.
Named entity
recognition
7. Speech / Audio AI
Abbreviation
Full Form
Short Detail
Example
ASR
Automatic Speech
Recognition
Converts speech into
text.
Voice typing
TTS
Text-to-Speech
Converts text into
voice.
AI voice reader
STT
Speech-to-Text
Same as ASR.
Dictation app
8. Computer Vision
Techniques
Abbreviation
Full Form
Short Detail
Example
CV
Computer Vision
AI for images and
videos.
Object detection
OCR
Optical Character
Recognition
Reads text from
images.
Scanned documents
CNN
Convolutional Neural
Network
Main model for image
tasks.
Face recognition
YOLO
You Only Look Once
Fast object
detection model.
Detecting
cars/people
RCNN
Region-Based CNN
Object detection
model.
Detecting objects in
images
9. Model Error / Loss
/ Evaluation Metrics
Abbreviation
Full Form
Short Detail
Example
MSE
Mean Squared Error
Average squared
prediction error.
Regression error
MAE
Mean Absolute Error
Average absolute
prediction error.
House price error
RMSE
Root Mean Squared
Error
Square root of MSE.
Forecast error
R²
R-Squared
Shows how well model
explains data.
Regression accuracy
CE
Cross Entropy
Loss for
classification.
Image classification
BCE
Binary Cross Entropy
Loss for two-class
problems.
Spam / not spam
Acc
Accuracy
Correct predictions
out of total.
Test accuracy
F1
F1 Score
Balance of precision
and recall.
Medical detection
AUC
Area Under Curve
Measures
classification performance.
Fraud detection
10. Training /
Optimization Terms
Abbreviation
Full Form
Short Detail
Example
GD
Gradient Descent
Reduces model error
step by step.
Training ML model
SGD
Stochastic Gradient
Descent
Faster version of
gradient descent.
Deep learning
training
LR
Learning Rate
Step size during
training.
Model optimization
ReLU
Rectified Linear
Unit
Activation function.
CNN hidden layers
BP
Backpropagation
Updates neural
network weights.
Training ANN
RLHF
Reinforcement
Learning from Human Feedback
Improves AI using
human feedback.
Chatbot improvement
11. Data Processing /
Feature Techniques
Abbreviation
Full Form
Short Detail
Example
PCA
Principal Component
Analysis
Reduces number of
features.
Image compression
EDA
Exploratory Data
Analysis
Understanding data
before modeling.
Finding trends
FE
Feature Engineering
Creating useful
input features.
Age group from age
ETL
Extract, Transform,
Load
Data preparation
process.
Data warehouse
API
Application
Programming Interface
Connects software
with AI model.
Using ChatGPT in app
MCQ Memory Tip
Models / Techniques: CNN, RNN, GAN, BERT, KNN, SVM, RF Loss / Error Functions: MSE, MAE, RMSE, CE, BCE AI Areas: NLP, CV, ASR, TTS Main ML Categories: Supervised, Unsupervised, Reinforcement
