Here is a brief diary of topics discussed in classes.
Slides and coding scripts are distributed after each lecture via the Google groups mailing-list. Refer to the home page on how to subscribe.
[19/09/2022] Introduction to Fundamentals of Data Science.
[22/09/2022] Introduction to Digital image processing and computer vision.
[29/09/2022] Image filtering, linear filters, and convolutions.
[03/10/2022] Smoothing and derivative filters, multi-scale image representations, and edge detection.
[06/10/2022] Representing images with histograms of colors and image classification with the nearest neighbor algorithm
[10/10/2022] Performance evaluation and introduction to linear regression.
[13/10/2022] Linear regression, mean squared error, and gradient descent.
[17/10/2022] Gradient descent for multivariate linear regression, polynomial regression, and the normal equation.
[20/10/2022] The probabilistic interpretation of least squares, and locally-weighted regression.
[31/10/2022--online recording] Classification with logistic regression, the probabilistic interpretation of the hypothesis, MLE for logistic regression.
[03/11/2022] Newton's method for logistic regression, the exponential family of distributions, the generalized linear model.
[07/11/2022] Multinomial Classification, Softmax Regression and Cross Entropy.
[10/11/2022] Image Classification, Linear Classifiers and Multinomial Logistic Regression.
[14/11/2022] Parameter Optimization with Gradient Descent and Image Features.
[17/11/2022] The Computational Graph and Backpropagation.
[21/11/2022] First Student Project Presentations.
[24/11/2022] Neural Networks.
[28/11/2022] Convolutional Neural Networks; Introduction to Generative Models and Gaussian Discriminant Analysis.
[1/12/2022] Relation between GDA and Logistic Regression; and Naive Bayes, including application to Spam Filtering.
[5/12/2022] Multinomial Classification with Naive Bayes and Laplace Smoothing.
[12/12/2022] The Bias-Variance tradeoff.
[15/12/2022] Regularization, Cross Validation and Feature Selection.
[19/12/2022] Final Student Project Presentations.
[23/09/2022] Introduction to Python, data types, mutability, if statements, loops, and zip().
[30/09/2022] Matrices, vectors and files.
[07/10/2022] Introduction to Numpy, multi-dimensional arrays, indexing, slicing, sub-arrays.
[14/10/2022] Numpy array operations, universal functions (ufuncs) and broadcasting.
[21/10/2022] Numpy Boolean arrays and their use as masks, Boolean logic, and fancy indexing.
[04/11/2022] Introduction to Pandas, the Series, Dataframe and Index objects; data indexing and selection.
[11/11/2022] Data operations in Pandas, Hierarchical indexing, Concat and Append.
[18/11/2022] Merge and Joins, and Practical Review of Pandas.
[25/11/2022] Pytorch for Deep Neural Networks modelling and training; Introduction to Visualization with Matplotlib.
[02/12/2022] Line plots, scatter plots, Bar plots, error bars, Density and Contour plots with Matplotlib.
[09/12/2022] Machine Learning with Scikit-Learn, including data representation and the estimator API; Hyperparameters and Model Validation.
[16/12/2022] Scikit-Learn for Feature Engineering, Linear Regression including Regularization, and (Gaussian) Naive Bayes.