1-10: AI Fundamentals
1.Artificial Intelligence (AI) – The simulation of human intelligence in machines. Example: AI powers voice assistants like Siri and Alexa.
2.Machine Learning (ML) – A subset of AI where computers learn from data. Example: Netflix recommends shows based on your watch history using ML.
3.Deep Learning (DL) – A type of ML using neural networks with multiple layers. Example: Self-driving cars use deep learning to detect pedestrians.
4. Neural Network – A system of algorithms inspired by the human brain. Example: Facial recognition on smartphones uses neural networks.
5.Supervised Learning – ML where models learn from labeled data. Example: Email spam filters learn from labeled emails (spam or not spam).
6.Unsupervised Learning – ML where models find patterns in unlabeled data. Example: AI clusters customers into groups based on shopping behavior.
7.Reinforcement Learning – ML where an agent learns by trial and error. Example: AI plays chess by learning from winning and losing moves.
8.Model – A mathematical representation of patterns in data. Example: A weather prediction model forecasts rain based on past climate data.
9.Algorithm – A set of rules for solving a problem. Example: Google search uses PageRank algorithm to rank web pages.
10.Data Science – The field combining statistics, ML, and domain knowledge. Example: A data scientist analyzes sales data to predict future trends.
11-20: Data & Preprocessing
1.Dataset – A collection of data used for training or testing AI models.
Example: MNIST dataset contains images of handwritten digits for AI training.
2.Feature – A measurable property or characteristic of data.
Example: Height, weight, and age are features in a health dataset.
3.Label – The target output in supervised learning.
Example: In spam detection, “Spam” or “Not Spam” is the label.
4.Feature Engineering – Selecting and transforming data for better ML performance. Example: Creating “Total Purchase Value” from quantity and price columns.
5.Normalization – Scaling data to a standard range.
Example: Converting age (20-80) to a 0-1 scale helps models learn better.
6.Overfitting – A model performs well on training data but poorly on new data. Example: A model memorizes training data but fails on unseen images.
7.Underfitting – A model fails to learn patterns from data.
Example: A model predicts house prices too simply, ignoring key factors.
8.Data Augmentation – Expanding the dataset using modified versions of existing data. Example: Flipping images horizontally to create more training data.
9.Dimensionality Reduction – Reducing the number of features to simplify analysis. Example: Removing irrelevant features to improve model efficiency.
10.Principal Component Analysis (PCA) – A technique for reducing dimensions while preserving information. Example: PCA can reduce 100 features to 10 in an image dataset.
31-40: AI Applications & Concepts
1.Natural Language Processing (NLP) – AI that enables computers to understand language.
Example: AI translates languages in Google Translate.
2.Computer Vision – AI that enables machines to interpret images.
Example: AI detects faces in smartphone cameras.
3.Speech Recognition – AI converts speech into text.
Example: Google Assistant transcribes spoken words.
4.Chatbot – An AI system that interacts with users.
Example: Customer support bots answer FAQs.
5.Recommendation System – Suggests items based on user behavior.
Example: Spotify recommends songs based on listening history.
6.Autonomous Vehicles – AI-powered self-driving technology.
Example: Tesla’s autopilot uses AI for navigation.
7.Generative AI – AI that creates new content.
Example: ChatGPT generates text, Mid journey creates images.
8.Transfer Learning – Using a pre-trained model for a new task.
Example: Using a pre-trained image model to detect medical conditions.
9.Bias in AI – Unfair predictions due to biased data.
Example: AI favors one gender in hiring decisions due to biased training data.
10.Explainability (XAI) – Making AI decisions understandable.
Example: AI explains why a loan application was rejected.
41-50: AI Tools & Technologies
1.TensorFlow – A deep learning framework.
Example: Used for image recognition in Google Photos.
2.PyTorch – A deep learning framework widely used in research.
Example: Used in AI-generated art projects.
3.OpenCV – A library for computer vision tasks.
Example: AI detects objects in security cameras using OpenCV.
4.Scikit-learn – A library for ML algorithms.
Example: Used for predicting customer churn.
5.Jupyter Notebook – An interactive coding environment for AI.
Example: AI engineers write Python code for ML models in Jupyter.
6.Google Colab – A cloud-based Jupyter Notebook.
Example: Running AI models without needing a powerful PC.
7.API (Application Programming Interface) – A way for software to communicate.
Example: AI-powered voice assistants use APIs to fetch responses.
8.Edge AI – AI models running on devices instead of cloud servers.
Example: AI-powered smart cameras process video on-device.
9.Turing Test – A test for human-like AI intelligence.
Example: Chatbots attempt to pass the Turing Test in conversation.
10.AGI (Artificial General Intelligence) – A theoretical AI with human-like intelligence.
Example: An AI that thinks and learns like a human.