Before my masters in Computer Science at Columbia, I was an undergraduate in Chemical Engineering, and strengthened my knowledge of ML through various electives, online courses and internships. I have mentioned some of the ones which have helped me most in my ML projects below.
I truly believe in the power of interdisciplinary studies and feel that having a strong foundation in CS along with other fields would foster very innovative ideas and directions (like Alphafold). An instance of this is from my work on CausalCite where because of a certain unique distribution of the metric we were comparing various sampling methods, and finally we went with my proposed approach which was inspired from a Numerical Methods course of Chemical engineering.
Courses at Columbia – Spring 2025
| Course Code | Title | Description | Instructor(s) |
|---|---|---|---|
| COMS6998 | Applied Machine Learning on the Cloud | Training and deploying ML/DL systems on cloud environments using scalable infrastructure. Includes AWS, Azure, distributed pipelines, and monitoring models in production. | Prof. I-Hsin Chung, Prof. Seetharami Seelam |
| COMS W4111 | Introduction to Databases | Relational algebra, SQL, schema design, indexing, transactions, and database internals. | Prof. Kenneth Ross |
| COMS W4732 | Computer Vision II: Learning | Deep learning for vision tasks, including detection, segmentation, self-supervised learning, and video understanding. | Prof. Carl Vondrick |
| EECS 6998 | Reinforcement Learning | Advanced topics in RL, exploration/exploitation, policy gradients, and theoretical foundations. | Prof. Javad Ghaderi |
TA Role: Teaching Assistant for "Neural Networks and Deep Learning" by Prof. Richard Zemel
Courses at Columbia Fall 2024
| Course Code | Title | Description | Instructor |
|---|---|---|---|
| COMS6998 |
High Performance Machine Learning | HPC techniques typically applied to supercomputing software and AI Algos Building efficient AI systems using compression, pruning, quantization, knowledge distillation, neural architecture search, data/model parallelism, and distributed training. Using fast math libraries, CUDA, and C++ to accelerate High Performance AI algorithms. |
Prof Kaoutar El Maghraoui |
| COMS6998 | Deep Learning and LLM based Generative AI Systems | ML/LLM model lifecycle and steps in making a trained model production ready, MLOps, DL/LLM models on cloud platforms using GPUs, LLM benchmarks and performance metrics | Prof Parijat Dube and Prof. Chen Wang |
| EECS 6994 | GenAI and Modern Deep Learning | LLMs, GenAI in vision, Safety - security/privacy/fairness | Prof Micah Goldblum |
| COMS4705 | Natural Language Processing | NLP techniques for language modeling, tagging, parsing, and word-sense disambiguation. Applications like discuss applications such as machine translation, summarization, question answering, dialog systems, and caption generation. | Prof Daniel Bauer |
| CSOR 4231 | Analysis of Algorithms | Sorting, Searching, Graphs, Linear Programming, NP Completeness. | Prof Alex Andoni |
Transcript Courses from IIT Roorkee
| Course Code | Title | Description | Course Structure |
|---|---|---|---|
| MAN-001 |
Mathematics - 1 | Matrix Algebra, Differential Calculus, Integral Calculus, Vector Calculus | link |
| CHN-103 | Computer Programming and Numerical Analysis |
C++, Data Structures, Pointers, Object Oriented Programming, Numerical Methods. | link |
| MAN-002 | Mathematical Methods | Ordinary, Partial Differential Equations, Z transforms, Laplace, Fourier. | link |
| HSS-01 | Economics | Micro and Macro Economics, Production functions, Cobb-Douglas production function, break-even analysis | link |
| CHN-323 | Computer Applications in Chemical Engineering | Solution of homogeneous set of linear equations using eigen values and eigen vectors, Boundary value problems, finite difference techniques. | link |
| IEE-03 | Artificial Neural Networks and Applications | Fuzzy Logic, SVMs, Loss Functions, ANNs, RNNs, LSTMS, CNNs, SVM, | |
| NOC21-CS34 | Discrete Mathematics | Sets, Relations, Functions, Graph Theory. | link |
| CHE-515 | Computational Fluid Mechanics | Finite Difference Method, Finite Volume Method, Finite Element Method | link |
MOOCs from other universities, done online
| Course Code | Title | Description | Course Structure |
|---|---|---|---|
| CS231n |
CNNs for Visual Recognition | Regularization and Optimization, Backprop, CNNs, RNNs, Transformers. The course that got me hooked on DL! | link |
| CS224n | NLP with Deep Learning | Vector Embeddings, RNNs, LSTMs, Seq2Seq models, Self Attention, 1D ConvNets, Multimodal | link |
| Stats -110 | Statistics 110: Probability | Probability, Distributions, MGFs, Markov Chain, Stats | link |
| MIS-SEM | Missing Semester of Your CS Education | Shell, Vim, Git, Debugging, Metaprogrammming | link |
| fast.ai | Practical Deep Learning | Building, deploying ML models, Random forests and gradient boosting, Transfer learning | link |
| IEE-03 | Artificial Neural Networks and Applications | Fuzzy Logic, SVMs, Loss Functions, ANNs, RNNs, LSTMS, CNNs, SVM, | |
| CS229 | Machine Learning | Bias/variance, Regression, Classification, Bagging, Boosting, K-Means, PCA | link |
| RL-101 | Introduction to Reinforcement Learning | Markov Decision Process, Policy Gradient, Model Free prediction, etc | link |