Lectures
You can download the lectures here. We will try to upload lectures prior to their corresponding classes.
-
-
Lec2 - Linear Classifiers and Perceptron
Summary: Basics of Supervised Learning, Classification and the Perceptron Algorithm
[slides]
-
Lec3 - Multilayer Perceptron and Intro to Deep Learning
Summary: Evolving the perceptron model into Multiclas and Multilayer Perceptrons
[slides]
-
Lec4 - Optimization and Regularization
Summary: Gradiente Descent, Modern Optimizers and Regularizers
[slides]
-
-
Lec6 - Pytorch II – Images and Regularization
Summary: Using images, batch normalization and dropout in Pytorch
[slides]
-
Lec7 - Convolutional Neural Networks
Summary: Convolution operation, Representation Learning with CNNs
[slides]
-
-
Lec9 - Transfer Learning and Residual Nets
Summary: Transfer Learning/Fine Tunning with VGG and Resnets
[slides]
-
Lec10 - Inception Net and what CNNs learn
Summary: Branching Nets, 1x1 convolution, Inception, Deep Dream
[slides]
-
Lec11 - Adversarial Examples and Self-supervision
Summary: Ways to break networks' results and learn without labels
[slides]
-
-
Lec13 - Intro to Object Detection
Summary: Localization and Detection tasks, Naive Detection, RCNN
[slides]
-
-
Lec15 - Intro to Image Segmentation
Summary: Semantic and Instance Segmentation, UNet and Mask-RCNN
[slides]
-
Lec16 - Applications of Detection and Segmentation
Summary: Pose and Keypoint Detection, Face Recognition, Gaze Estimation
[slides]
-
Lec17 - Autoencoders
Summary: Autoencoders and the tasks in CV that can be solved with them.
[slides]
-
Lec18 - Image Generation with GANs
Summary: Simple Generative Adversarial Networks and DCGAN
[slides]
-
-
-
Lec21 - Transformers and ChatGPT
Summary: Dive into the transformer architecture, its use in CV and in ChatGPT.
[slides]
-
Lec22 - Image Generation by Prompt
Summary: Contrastive Learning via CLIP and Stable Diffusion
[slides]