Information Technology is coming soon
We're still writing and reviewing the notes for every subject, and we'll open it when every subject is ready. Meanwhile you can practise aptitude, ask Aria about any subject, or see the branches that are ready.
Information Technology
Artificial Intelligence & Machine Learning
Agents and search, logic, supervised and unsupervised learning, SVMs and ensembles.
Notes for Artificial Intelligence & Machine Learning are being written and reviewed. Until they're up, Aria teaches every topic — ask for any part of the syllabus, with worked numericals.
Coming next in Artificial Intelligence & Machine Learning
- AI: history and types· notes coming
- AI, ML, deep learning and data science· notes coming
- Intelligent agents and PEAS· notes coming
- Types of agents· notes coming
- Problem formulation and state space· notes coming
- Uninformed search: BFS, DFS and uniform cost· notes coming
- Informed search: greedy best-first and A*· notes coming
- Hill climbing and local search· notes coming
- Propositional and predicate logic· notes coming
- Forward and backward chaining, expert systems· notes coming
- Machine learning workflow· notes coming
- Data preprocessing· notes coming
- Linear and polynomial regression· notes coming
- Logistic regression· notes coming
- Decision trees· notes coming
- K-nearest neighbours and naïve Bayes· notes coming
- Evaluating classifiers· notes coming
- K-means clustering· notes coming
- Hierarchical clustering and DBSCAN· notes coming
- Association rule mining· notes coming
- PCA and dimensionality reduction· notes coming
- Feature selection and cluster evaluation· notes coming
- Support vector machines· notes coming
- Ensembles: bagging, random forest and boosting· notes coming
- Introduction to reinforcement learning· notes coming
- Cross-validation and hyperparameter tuning· notes coming
- Bias–variance trade-off and responsible AI· notes coming
- Concept learning: Find-S and candidate elimination· notes coming
- Evaluating hypotheses· notes coming
- Linear discriminant analysis· notes coming
- Regularisation, early stopping and dropout· notes coming
- Perceptrons and multilayer perceptrons· notes coming
- Backpropagation in feedforward networks· notes coming
- Gradient descent optimisers: momentum to Adam· notes coming
- CNN architectures: LeNet to ResNet· notes coming
- Visualising convolutional networks· notes coming
- Recurrent networks and backpropagation through time· notes coming
- LSTM and GRU· notes coming
- AI problems and techniques: tic-tac-toe· notes coming
- Production systems and problem characteristics· notes coming
- Depth-limited and bidirectional search· notes coming
- Simulated annealing, beam search and genetic algorithms· notes coming
- Constraint satisfaction problems· notes coming
- Adversarial search: minimax and alpha-beta pruning· notes coming
- Knowledge representation and resolution· notes coming
- Bayesian networks and Dempster-Shafer theory· notes coming
- Planning: goal stack and hierarchical planning· notes coming
- NLP in AI: syntactic, semantic and pragmatic processing· notes coming
- Learning: inductive, explanation-based, neural and genetic· notes coming
- Expert systems and fuzzy logic· notes coming
- Well-posed learning problems and designing a learning system· notes coming
- Bayesian learning: MAP, MDL, Bayes optimal and Gibbs· notes coming
- PAC learning and VC dimension· notes coming
- Autoencoders: denoising, sparse and contractive· notes coming
- Loss functions, Lasso and Ridge regression· notes coming