Things I studied at Columbia.
Looks like Columbia is more sensitive about us sharing our work than Telecom. This repo contains a few group projects that are already publicly available, as well as some labs instructors authorized us to share. In the mean time, you might find some useful code in the Telecom folder.
Feel free to email me ([email protected]) or message me (https://www.linkedin.com/in/maxime-tchibozo/) for more information on the private stuff.
| Course | Labs/Projects |
|---|---|
| Capstone Project | First Report |
| Second Report | |
| Final Report | |
| Code Repository | |
| Presentation Video | |
| Foundations of Graphical Models (David M. Blei) | Reading Reports |
| Homework 0: Basic Probability and Statistics | |
| Homework 1: MCMC, Gibbs Sampling | |
| Homework 2: Variational Inference, Mixed-Membership Models | |
| Final Project: Identifying Bias in Text (supervised LDA - sLDA) | |
| Bayesian Models for Machine Learning (John Paisley) (Private) | HW1: EM Algorithm, MCMC |
| HW2: Variational Inference, MAP estimation | |
| HW3: Mixture Models, Bayesian nonparametric Gibbs sampler |
| Course | Labs/Projects |
|---|---|
| Computer Systems for Data Science | SQL, Google Cloud Platform |
| ACID, Transactions, 2-Phase Locking | |
| Apache Spark, GCP | |
| Tensoflow, Google Cloud | |
| Applied Machine Learning | Visualisation |
| Scikit-learn Tricks | |
| Feature Engineering | |
| Transformers, BERT | |
| Deep Learning | |
| Machine Learning (Private) | HW1: Maximum Likelihood, Bias-Variance Tradeoff |
| HW2: Linear Classifiers, Decision Trees | |
| HW3: Optimisation, Logistic Regression, SVM | |
| HW4: Optimisation, Neural Networks, Kernels | |
| Causal Inference for Data Science | HW1: Counterfactuals, Causal Effects, Experiment Design |
| HW2: Bayesian Graphs, Backdoor Sets | |
| HW3: Propensity Scoring, Doubly Robust Treatment Effect Estimation | |
| HW4: Instrumental Variables, Mechanisms, Front-Door Criterion |
| Course | Labs/Projects |
|---|---|
| Exploratory Data Analysis and Visualisation (Private) | Project |
| Community Contribution | |
| Problem Set 1: tidyr, Shapiro test, histograms | |
| Problem Set 2: ggplot2, Cleveland plots, web scraping | |
| Problem Set 3: likert, parallel coordinate plots | |
| Problem Set 4: tidyquant, D3, missing values, time series | |
| Problem Set 5: SVG, D3, interactive web app | |
| Statistical Inference and Modeling (Private) | HW1: Estimation, Rao-Blackwell |
| HW2: Survival Data, Missing Data, Markov Chains, Time Series | |
| HW3: Linear Models, Generalised Linear Models | |
| HW4: Generalised Additive Models, Hypothesis Testing | |
| Algorithms for Data Science (Private) | HW1: Complexity, Sorting Algorithms |
| HW2: Dynamic Programming, Trees, Graph Algorithms | |
| HW3: Flow Networks, Linear Programming | |
| HW4: Graphs, Flow, NP-Completeness, Integer Programming | |
| Machine Learning for Image Analysis (Private) | HW1: KMeans for Face Recognition |
| HW2: Analysing fMRI Data, SPM12 | |
| HW3: Brain Data Classification, PCA, SVM, Neural Networks | |
| Iris Recognition Group Project (w. Hariz Johnson) | |
| Digit Recognition Project, Convolutional Neural Networks |