SUBHANKAR MISHRA

ଶୁଭଙ୍କର ମିଶ୍ର

Assistant Professor in School of Computer Sciences (CSS), NISER
smishra@niser.ac.in | +916742494460 | Bhubaneswar, Odisha, India - 752050
Machine Learning & Privacy
Lab page | CV | Google Scholar | Github | Map

---

CS460/660 - Machine Learning

Syllabus

• Learning, Inductive Bias, Features, Labels, Basics of Statistics and Probability
• Supervised Learning - Some models
• Ensemble Methods: Bagging, Boosting. Learning Theory
• Unsupervised Learning - Some models
• Reinforcement Learning (if time permits)

Prerequisite

• Algorithms (CS301 or equivalent)
• Basic Programming Skills

Grading Scheme

• Assignments - 60 marks
• Project - 40 marks
• Mid-Term - No midterm
• End-Term - 40 marks
• *In case, there is no endterm, total marks will be based on Assignments

---

Lectures

• Week 01:
  • Lecture 1: Introduction
  • Lecture 2: Machine Learning - Types (Prediction)
  • Lecture 3: Inductive Bias
• Week 02:
  • Lecture 4: Machine Learning - Types (Input)
  • Lecture 5: Supervised Learning - How it works?
• Week 03:
  • Lecture 6: Mathematics for ML
  • Lecture 6_1: Confidence Interval
  • Lecture 6_2: Hypothesis Testing (Significance Tests)
  • Lecture 7: Linear Regression
  • Lecture 7_1: PAC Learning
  • Lecture 8: Gradient Descent (Linear Regression)
  • Lecture 8_1: Linear Regression with multiple features
• Week 04: Project Proposal Presentation
• Week 05:
  • Lecture 9: Logistic Regression
  • Lecture 10: k-Nearest Neighbour
  • Lecture 11: Decision Tree (Gini Impurity)
  • Lecture 11_1: Decision Tree (ID3 Algorithm)
  • Lecture 11_2: Decision Tree(Regression)
• Week 06:
  • Lecture 12: Support Vector Machine
  • Lecture 13: Support Vector Machine - Kernels
  • Lecture 13_1: Support Vector Machine - Regression
• Week 07:
  • Lecture 14: Feature Engineering
  • Lecture 15: Bias-Variance Tradeoff, Regularization
  • Lecture 16: Model Assessment
• Week 08: Project Milestone Presentation
• Week 09:
  • Lecture 17: Perceptron (Convergence)
  • Lecture 18: Perceptron Implementation
  • Lecture 19: Multi-Layer Perceptron
  • Lecture 19_1: Backpropagation
• Week 10:
  • Lecture 20: Ensemble Method - Bagging
  • Lecture 21: Ensemble Method - Boosting (Regression)
  • Lecture 21_1: Ensemble Method - Boosting (Classification)
• Week 11:
  • Lecture 22: Unsupervised - Clustering KMeans
  • Lecture 23: Unsupervised - Clustering DBSCAN
  • Lecture 24: Unsupervised - Dimensionality Reduction PCA
  • Lecture 24_1: Unsupervised - Dimensionality Reduction UMAP
  • Lecture 24_2: Unsupervised Algorithms - Dimensionality Reduction Autoencoder
  • Lecture 25: Naive Bayes Classifier
• Week 12: Project Final Presentation
• Week 13: Project Final Presentation
  Project Report Submission

---

Assignments

• [10] Assign 1: Prepare lecture note.
  Format will be a webpage with the same template as this website. It will be linked from this website and hosted on the NISER server. Sample template
• [10] Quizzes: Quizzes taken on Thursdays

---

Project

2020 Odd Semester Projects
A group of 2. Projects may involve

• Empirical Analysis
• Developing new algorithms
• Theoretical Project

Sample Projects All deliverables (reports) will be a webpage with the same template as this website. It will be linked from this website and hosted on the NISER server.

1. [05] Project Proposal - 10 mins
2. [05] Project Milestone - 10 mins
3. [15] Final Project Presentation - 25 mins + 5 mins for Q&A
4. [15] Project Report
5. [05] Extra Credit - Project yields significant result [Paper has been communicated to a conference/journal]

---

Books

Some recommended books on Machine learning.

• The Elements of Statistical Learning Link
• Mathematics for Machine Learning Link
• Introduction to Machine Learning with Python Link
• A course in Machine Learning Link

---

Academic Integrity

Any plagiarism, copying, allowing copying, unpermitted aid will lead to 'zero' in the assignment/exam/project.

---