| Date |
Topics |
| Jan 5, 2026 |
Introduction to inverse and optimization problems, linear regression
[MP4]
[PDF]
|
| Jan 8, 2026 |
Introduction to deep learning, perceptron, neurons, activation functions, loss functions, simple linear regression, steepest descent method
[MP4]
[PDF]
|
| Jan 12, 2026 |
Polynomial regression, multiple linear regression, metric space, normed space, inner product space, Hilbert space, Euclidean space, linear functional, Riesz representation theorem
[MP4]
[PDF]
|
| Jan 15, 2026 |
Various spaces, Frechet and Gateaux derivatives, batch gradient descent (BGD), stochastic gradient descent (SGD), minibatch gradient descent (MGD)
[MP4]
[PDF]
|
| Jan 19, 2026 |
Linear conjugate gradient, underdetermined linear system and a minimum-norm straint, Tikhonov regularization
[MP4 (part 1),MP4 (part2)]
[PDF]
|
| Jan 22, 2026 |
multiple linear regression, single-layer perceptron, multilayer perceptron (MLP), parameter vs hyperparameter, data splitting (training, validation, test sets), overfitting problem, ridge regression (L2 regularization), lasso regression (L1 regularization), coordinate descent algorithm
[MP4]
[PDF]
|
| Jan 29, 2026 |
Forward propagation, backpropagation, training neural networks
[MP4]
[PDF]
|
| Feb 5, 2026 |
Introduction to Keras, SGD and its variants
[MP4]
[PDF]
|
| Feb 12, 2026 |
Methods for computing gradients: numerical differentiation, symbolic differentiation, and automatic differentiation
[MP4]
[PDF]
|
| Feb 19, 2026 |
Multiple linear regression and MLP using Keras, function approximation and Universal Approximation Theorem
[MP4]
|
| Feb 26, 2026 |
Solving differential equations using neural networks, statistics, information theory, classification problems, Initialization and normalization, hyperparameter tuning, dropout, |
| Mar 12, 2026 |
convolution, pooling layers, CNN architectures, data augmentation, image classification |
| Mar 19, 2026 |
Object detection, image segmentation |
| Mar 26, 2026 |
Transfer learning and fine tuning |
| Apr 2, 2026 |
Recurrent neural networks (RNNs), vanishing gradients, GRU, LSTM, word embeddings |
| Apr 9, 2026 |
Transformer architecture: self-attention, multi-head attention, positional encoding |
| Apr 16, 2026 |
Autoencoder, variational autoencoder (VAE), Generative adversarial network (GAN) |
| Apr 23, 2026 |
Large language models (LLMs) |
| May 7, 2026 |
Project presentation |