Alfredo Canziani Courses

Learning the Feature Vector - Lecture 20

Dive into feature vector learning with Alfredo Canziani's NYU undergraduate lecture, exploring deep learning concepts through spiral classification examples.

• YouTube
• 1 hour 9 minutes
• Self-Paced
• Free Video

NYU Artificial Intelligence - Introduction to Machine Learning Fundamentals

Discover fundamental AI concepts including Naïve Bayes classification, perceptron algorithms, logistic regression, and optimization techniques through NYU's comprehensive curriculum.

• YouTube
• 6 hours 11 minutes
• Self-Paced
• Free Video

NYU Deep Learning - Fall 2022

Master neural network inference, energy-based classification, and latent variable models through PyTorch implementations and backpropagation techniques.

• YouTube
• 8 hours 30 minutes
• Self-Paced
• Free Video

NYU Deep Learning - Spring 2020

Master neural networks, CNNs, RNNs, GANs, and transformers through hands-on PyTorch implementation covering optimization, energy-based models, and applications in CV and NLP.

• YouTube
• 1 day 17 hours 12 minutes
• Self-Paced
• Free Video

Course Introduction and McCulloch & Pitts Binary Neuron - Lesson 01

Discover the fundamentals of neural networks starting with the historic McCulloch & Pitts binary neuron model in this introductory deep learning lesson.

• YouTube
• 30 minutes
• Self-Paced
• Free Video

Programming a Neural Network - Lesson 02

Dive into neural network programming fundamentals through hands-on coding exercises and practical implementation techniques.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

Inference with Neural Nets

A focused introduction to inference with neural networks, connecting mathematical ideas such as singular vectors with PyTorch implementation.

• YouTube
• 1 hour 7 minutes
• Self-Paced
• Free Video

PCA, AE, K-Means, Gaussian Mixture Model, Sparse Coding, and Intuitive VAE

An intuitive tour of unsupervised representation learning, from PCA, autoencoders, and clustering to sparse coding and variational autoencoders.

• YouTube
• 1 hour 54 minutes
• Self-Paced
• Free Video

Differentiable Associative Memories, Attention, and Transformers

Explores reasoning and planning through energy minimization, differentiable associative memory, attention, and transformer architectures.

• YouTube
• 2 hours
• Self-Paced
• Free Video

Self-Supervised Learning and Variational Inference

A lecture on self-supervised learning through sparse modeling, amortized inference, temporal consistency, and probabilistic interpretations of VAEs.

• YouTube
• 1 hour 55 minutes
• Self-Paced
• Free Video

Prediction and Planning Under Uncertainty

Introduces model predictive control for prediction and planning in stochastic environments using visual representations and lane costs.

• YouTube
• 1 hour 15 minutes
• Self-Paced
• Free Video

Latent Variable EBMs for Structured Prediction

Examines latent-variable energy-based models for structured prediction, from contrastive training and joint embeddings to factor graphs, Viterbi decoding, and graph transformer networks.

• YouTube
• 1 hour 49 minutes
• Self-Paced
• Free Video

Joint Embedding Method and Latent Variable Energy Based Models

Explores how joint embeddings and latent variables define and train energy-based models through inference, probabilities, and specialized loss functions.

• YouTube
• 1 hour 52 minutes
• Self-Paced
• Free Video

The Truck Backer-Upper

Train a recurrent neural network controller to back a trailer truck into a parking position, using simulated dynamics and backpropagation through time.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

ConvNets in Practice

Explore how convolutional networks support object detection, face detection, semantic segmentation, and efficient vision systems.

• YouTube
• 52 minutes
• Self-Paced
• Free Video