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.
[25/09/2023] Introduction to the course, preliminaries on data science, machine learning and computer vision.
[29/09/2023] Introduction to Digital image processing and computer vision.
[9/10/2023] Image filtering, linear filters, and convolutions.
[13/10/2023] Smoothing and derivative filters, multi-scale image representations, and edge detection.
[16/10/2023] Representing images with histograms of colors and image classification with the nearest neighbor algorithm, and performance evaluation.
[20/10/2023] Introduction to linear regression
[23/10/2023] Linear regression, mean squared error, and gradient descent.
[27/10/2023] Gradient descent for multivariate linear regression, including mini-batch and stochastic gradient descent.
[30/10/2023] Polynomial regression, and the normal equation.
[3/11/2023] Locally-weighted regression.
[6/11/2023] The probabilistic interpretation of least squares.
[10/11/2023] Classification with logistic regression, the probabilistic interpretation of the hypothesis, MLE for logistic regression.
[13/11/2023] Newton's method for logistic regression, the exponential family of distributions.
[17/11/2023] The generalized linear model.
[20/11/2023] More on the generalized linear model and Multinomial Classification.
[23/11/2023] More on Softmax Regression and Cross Entropy; Image Classification.
[27/11/2023] First Student Project Presentations.
[1/12/2023] Parametric Linear Classifiers for Image Classification and Multinomial Logistic Regression.
[4/12/2023] Parameter Optimization with Gradient Descent; Image Features; The Computational Graph and Backpropagation.
[11/12/2023] Backpropagation for tensors and Neural Networks.
[15/11/2023] Convolutional Neural Networks.
[18/11/2023] Final Student Project Presentations.
[22/12/2023] Generative models; Naive Bayes, including application to Spam Filtering; Laplace Smoothing.
[28/09/2023] Introduction to Python, data types, mutability, if statements, loops, and zip().
[12/10/2023] Matrices, vectors and files.
[19/10/2023] Introduction to Numpy, multi-dimensional arrays, indexing, slicing, sub-arrays, Numpy array operations, universal functions (ufuncs).
[26/10/2023] More on Numpy: broadcasting, Boolean arrays and their use as masks, Boolean logic.
[2/11/2023] Fancy indexing and Introduction to Pandas, Series and Dataframe.
[09/11/2023] The Pandas Index objects; data indexing and selection; data operations in Pandas.
[16/11/2023] Pandas Hierarchical indexing, Concat and Append.
[23/11/2023] Merge and Joins, and Practical Review of Pandas.
[30/11/2023] Visualization with Matplotlib: line plots, scatter plots, bar plots, and error bars.
[07/12/2023] Machine Learning with Scikit-Learn, including data representation and the estimator API; Hyperparameters and Model Validation. Density and Contour plots with Matplotlib.
[14/12/2023] Pytorch for Deep Neural Networks modelling and training.
[21/12/2023] Scikit-Learn for Feature Engineering, Linear Regression, and Regularization.