Seventh Semester B.Tech Core Course Syllabus
Course Code: DA461 | Course Name: Bioinformatics | Credits: 2-0-2-6 |
---|---|---|
Pre-requisite: None | ||
Syllabus: Primer on molecular biology: Structure and function of nucleic acids and protein; genes and gene expression; the central dogma of biology; Sequencing, structure determination, and bioinformatics databases. Sequence alignment: Pairwise and multiple sequence alignment; Dynamic Programming; Global alignment; Local alignment; Scoring matrices and gap penalty; Carrillo–Lipman algorithm; Feng–Doolittle algorithm; CLUSTAL; Sequence logo. Pattern detection: Gibbs sampler; Hidden Markov model; Profile HMM Alignment. Phylogenetic analysis: Molecular evolution, homolog, orthologs, paralogs; Rooted and unrooted phylogenetic tree; Maximum parsimony method; Distance-based method; Genome assembly and next-generation sequencing: Shortest superstring approach; Overlap graph approach; de Bruijn graph approach; NGS read mapping; RNA-seq read mapping; Peak calling method. The lectures will focus on the well-established algorithms in these topics, and the laboratory exercises will supplement those lectures with programming assignments and mini projects. | ||
Textbooks:
|
||
References:
|
Course Code: DA462 | Course Name: Data Analytics for Finance | Credits: 3-0-0-6 |
---|---|---|
Pre-requisite: | ||
Syllabus: Asset pricing models, binomial model, geometric Brownian motion; Financial derivatives, options, forwards & futures, swaps; Black-Scholes equation, valuation of forwards, futures and swaps; Monte Carlo simulation, supervised learning for asset price prediction, ML model for pricing derivatives; Markowitz portfolio theory, Capital Asset Pricing Model, asset ranking, performance analysis; Portfolio management through clustering, RL based algorithm for portfolio allocation; Financial risk management, Basel regulations, credit risk, market risk, operational risk; ML in financial risk management, Value-at-Risk (VaR), estimating credit and operational risk. | ||
Textbooks:
|
||
References:
|
Course Code: DA421 | Course Name: FATE in AI Models | Credits: 3-0-0-6 |
---|---|---|
Pre-requisite: None | ||
Syllabus: Data: Protection rational & genesis, data protection in India (judicial developments on right to privacy, legislative developments); Territorial and Personal Scope; Personal data; Sensitive personal data; Processing of data; Processing of sensitive data; Rights: Introduction, right to object to processing, right to be forget; Case studies. Fairness: Introduction, sources of unfairness, definitions; Metrics for fairness, fair data; pre-processing methods; In-processing methods; post-processing methods; Model auditing for fairness; ML models and privacy; ML models and security; Fair product design & development; Laws for ML; Compliance tools: Anonymisation, Privacy by design. Accountability & Ethics: Introduction, Guidelines in AI ethics; AI in practice; Advances in AI ethics; Transparency (Explainability): Importance of explainability in AI systems, Case studies; Accuracy-interpretability tradeoff in machine learning; Different types of interpretability approaches: Rule-based, Prototype-based, Feature importance-based, post-hoc explanations. | ||
Textbooks:
|
||
References:
|