Machine Learning Syllabus, Exam Pattern

Machine Learning Syllabus

Machine Learning :

1. Foundations of Machine Learning

Introduction to Machine Learning: Definition, scope, applications

Types of Learning:

i. Supervised learning

ii. Unsupervised learning

iii. Semi-supervised learning

iv. Reinforcement learning

v. Basics of Linear Algebra, Probability, and Statistics for ML

vi. Overfitting, underfitting, bias-variance tradeoff

2. Supervised Learning Algorithms

Regression Techniques:

i. Linear regression, Multiple regression

ii. Polynomial regression

iii. Logistic regression

Classification Techniques:

i. k-Nearest Neighbors (k-NN)

ii. Naïve Bayes Classifier

iii. Decision Trees

iv. Random Forests

v. Support Vector Machines (SVM)

vi. Gradient Boosting methods (XGBoost, LightGBM, CatBoost)

vii. Evaluation Metrics: Accuracy, Precision, Recall, F1-score, ROC, AUC

3. Unsupervised Learning Algorithms

Clustering Methods:

i. k-Means clustering

ii. Hierarchical clustering

iii. DBSCAN

Dimensionality Reduction:

i. Principal Component Analysis (PCA)

ii. Linear Discriminant Analysis (LDA)

iii. t-SNE, UMAP

iv. Association Rule Learning: Apriori, FP-growth

4. Neural Networks & Deep Learning

i. Basics of Neural Networks: Perceptron, Multilayer Perceptron (MLP)

ii. Backpropagation and Gradient Descent

iii. Activation Functions

iv. Convolutional Neural Networks (CNNs)

v. Recurrent Neural Networks (RNNs), LSTMs, GRUs

vi. Autoencoders and Variational Autoencoders (VAE)

vii. Generative Adversarial Networks (GANs)

5. Optimization Techniques

i. Gradient Descent (Batch, Stochastic, Mini-batch)

ii. Learning rate schedules, momentum

iii. Adam, RMSProp, Adagrad, Nadam

iv. Regularization techniques (L1, L2, Dropout, Batch Normalization)

6. Reinforcement Learning (RL)

i. Basics of RL: Agent, Environment, Rewards, Policy, Value Function

ii. Dynamic Programming

iii. Monte Carlo Methods

iv. Temporal Difference (TD) Learning

v. Q-Learning & SARSA

vi. Deep Reinforcement Learning (DQN, Policy Gradients, Actor-Critic methods)

7. Probabilistic Models

i. Bayesian Networks

ii. Hidden Markov Models (HMMs)

iii. Gaussian Mixture Models (GMMs)

iv. Markov Decision Processes (MDPs)

8. Natural Language Processing (NLP)

i. Text preprocessing: Tokenization, Stop words, Lemmatization, Stemming

ii. Word Embeddings: Word2Vec, GloVe, FastText

iii. Transformers: Attention Mechanism, BERT, GPT

iv. Applications: Text classification, Sentiment analysis, Machine translation, Chatbots

9. Computer Vision (CV)

i. Image preprocessing techniques

ii. Feature extraction (SIFT, SURF, HOG)

iii. Object Detection: R-CNN, Fast R-CNN, YOLO, SSD

iv. Image Segmentation: U-Net, Mask R-CNN

10. Model Evaluation and Deployment

i. Cross-validation and resampling methods

ii. Hyperparameter tuning (Grid Search, Random Search, Bayesian Optimization)

iii. Model explainability (SHAP, LIME)

iv. ML Pipelines (Scikit-learn, TensorFlow, PyTorch, Keras)

v. Model Deployment (Flask, FastAPI, Docker, Cloud platforms)

11. Advanced Topics

i. Transfer Learning

ii. Few-Shot and Zero-Shot Learning

iii. Federated Learning

iv. Online Learning

v. Ethical AI and Fairness in ML

vi. Bias and Interpretability issues

Machine Learning Exam Pattern

Duration : 60 Minutes

No.of Question : 100

Total Marks : 100

Machine Learning Combo Packages

Machine Learning Free Mock Test

Quick View