Alfredo Canziani (冷在)

@UCupQLyNchb9-2Z5lmUOIijw - 43.7K subscribers

Music, math, and deep learning from scratch

Home Videos Live Playlists

Lesson 07 – A softer perceptron, part III: gradient descent

Lesson 07 – A softer perceptron, part III: gradient descent Alfredo Canziani (冷在)

2.4K views - 1 week ago

Lesson 06 – A softer perceptron, part II: likelihood and loss

Lesson 06 – A softer perceptron, part II: likelihood and loss Alfredo Canziani (冷在)

2.7K views - 1 month ago

Lesson 05 – A softer perceptron, part I: probabilities

Lesson 05 – A softer perceptron, part I: probabilities Alfredo Canziani (冷在)

1.3K views - 3 months ago

Lesson 04 – Bias, perceptron’s properties, and multi-class classification

Lesson 04 – Bias, perceptron’s properties, and multi-class classification Alfredo Canziani (冷在)

2K views - 4 months ago

Lesson 03 – Wiener’s cybernetics, Hebbian plasticity, and Rosenblatt’s perceptron

Lesson 03 – Wiener’s cybernetics, Hebbian plasticity, and Rosenblatt’s perceptron Alfredo Canziani (冷在)

2.7K views - 4 months ago

Lesson 02 – Programming a neural network

Lesson 02 – Programming a neural network Alfredo Canziani (冷在)

6.5K views - 4 months ago

Lesson 01 – Course intro and McCulloch & Pitts binary neuron

Lesson 01 – Course intro and McCulloch & Pitts binary neuron Alfredo Canziani (冷在)

14K views - 4 months ago

Lecture 20 – Learning the feature vector 𝒇(𝒙)

Lecture 20 – Learning the feature vector 𝒇(𝒙) Alfredo Canziani (冷在)

4.1K views - 1 year ago

Cosine (extract from undergrad DLSP25)

Cosine (extract from undergrad DLSP25) Alfredo Canziani (冷在)

2.3K views - 1 year ago

Chapter 2, video 4–6

Chapter 2, video 4–6 Alfredo Canziani (冷在)

1.1K views - 2 years ago

06 – Optimisation and gradient ascent

06 – Optimisation and gradient ascent Alfredo Canziani (冷在)

1.4K views - 2 years ago

05 – Multi-class perceptron, binary and multi-class logistic regression

05 – Multi-class perceptron, binary and multi-class logistic regression Alfredo Canziani (冷在)

1.4K views - 2 years ago

04 – Binary classifier evaluation, binary Perceptron

04 – Binary classifier evaluation, binary Perceptron Alfredo Canziani (冷在)

1.1K views - 2 years ago

Chapter 1, video 1–3

Chapter 1, video 1–3 Alfredo Canziani (冷在)

1.2K views - 2 years ago

03 – Naïve Bayes parameters estimation and Laplace smoothing

03 – Naïve Bayes parameters estimation and Laplace smoothing Alfredo Canziani (冷在)

1.5K views - 2 years ago

02 – Discrete probability recap, Naïve Bayes classification

02 – Discrete probability recap, Naïve Bayes classification Alfredo Canziani (冷在)

1.7K views - 2 years ago

00 – Course introduction

00 – Course introduction Alfredo Canziani (冷在)

6.9K views - 2 years ago

01 – Course first part recap, Naïve Bayes intro

01 – Course first part recap, Naïve Bayes intro Alfredo Canziani (冷在)

4.9K views - 2 years ago

14 – From latent-variable EBM (K-means, sparse coding) to target prop to autoencoders, step-by-step

14 – From latent-variable EBM (K-means, sparse coding) to target prop to autoencoders, step-by-step Alfredo Canziani (冷在)

2.8K views - 3 years ago

07 – Classification, an energy perspective – PyTorch 5-step training code

07 – Classification, an energy perspective – PyTorch 5-step training code Alfredo Canziani (冷在)

3.1K views - 3 years ago

06 – Classification, an energy perspective – Backprop and contrastive learning

06 – Classification, an energy perspective – Backprop and contrastive learning Alfredo Canziani (冷在)

4.8K views - 3 years ago

05 – Classification, an energy perspective – Notation and introduction

05 – Classification, an energy perspective – Notation and introduction Alfredo Canziani (冷在)

5.4K views - 3 years ago

03 – Inference with neural nets

03 – Inference with neural nets Alfredo Canziani (冷在)

12K views - 3 years ago

00 – Intro to NYU Deep Learning Fall 2022 playlist

00 – Intro to NYU Deep Learning Fall 2022 playlist Alfredo Canziani (冷在)

17K views - 3 years ago

10P – Non-contrastive joint embedding methods (JEMs) for self-supervised learning (SSL)

10P – Non-contrastive joint embedding methods (JEMs) for self-supervised learning (SSL) Alfredo Canziani (冷在)

4.7K views - 4 years ago

09P – Contrastive joint embedding methods (JEMs) for self-supervised learning (SSL)

09P – Contrastive joint embedding methods (JEMs) for self-supervised learning (SSL) Alfredo Canziani (冷在)

9.8K views - 4 years ago

14L – Lagrangian backpropagation, final project winners, and Q&A session

14L – Lagrangian backpropagation, final project winners, and Q&A session Alfredo Canziani (冷在)

6.1K views - 4 years ago

13L – Optimisation for Deep Learning

13L – Optimisation for Deep Learning Alfredo Canziani (冷在)

7.8K views - 4 years ago

07L – PCA, AE, K-means, Gaussian mixture model, sparse coding, and intuitive VAE

07L – PCA, AE, K-means, Gaussian mixture model, sparse coding, and intuitive VAE Alfredo Canziani (冷在)

11K views - 4 years ago

08L – Self-supervised learning and variational inference

08L – Self-supervised learning and variational inference Alfredo Canziani (冷在)

10K views - 4 years ago

09L – Differentiable associative memories, attention, and transformers

09L – Differentiable associative memories, attention, and transformers Alfredo Canziani (冷在)

9.9K views - 4 years ago

14 – Prediction and Planning Under Uncertainty

14 – Prediction and Planning Under Uncertainty Alfredo Canziani (冷在)

4.9K views - 4 years ago

06L – Latent variable EBMs for structured prediction

06L – Latent variable EBMs for structured prediction Alfredo Canziani (冷在)

11K views - 4 years ago

05L – Joint embedding method and latent variable energy based models (LV-EBMs)

05L – Joint embedding method and latent variable energy based models (LV-EBMs) Alfredo Canziani (冷在)

28K views - 4 years ago

13 – The Truck Backer-Upper

13 – The Truck Backer-Upper Alfredo Canziani (冷在)

3.5K views - 4 years ago

04L – ConvNet in practice

04L – ConvNet in practice Alfredo Canziani (冷在)

13K views - 4 years ago

03L – Parameter sharing: recurrent and convolutional nets

03L – Parameter sharing: recurrent and convolutional nets Alfredo Canziani (冷在)

23K views - 4 years ago

02L – Modules and architectures

02L – Modules and architectures Alfredo Canziani (冷在)

25K views - 4 years ago

01L – Gradient descent and the backpropagation algorithm

01L – Gradient descent and the backpropagation algorithm Alfredo Canziani (冷在)

66K views - 4 years ago

12 – Planning and control

12 – Planning and control Alfredo Canziani (冷在)

5.9K views - 5 years ago

12L – Low resource machine translation

12L – Low resource machine translation Alfredo Canziani (冷在)

4.1K views - 5 years ago

11 – Graph Convolutional Networks (GCNs)

11 – Graph Convolutional Networks (GCNs) Alfredo Canziani (冷在)

9.3K views - 5 years ago

10L – Self-supervised learning in computer vision

10L – Self-supervised learning in computer vision Alfredo Canziani (冷在)

33K views - 5 years ago

11L – Speech recognition and Graph Transformer Networks

11L – Speech recognition and Graph Transformer Networks Alfredo Canziani (冷在)

11K views - 5 years ago

10 – Self / cross, hard / soft attention and the Transformer

10 – Self / cross, hard / soft attention and the Transformer Alfredo Canziani (冷在)

37K views - 5 years ago

09 – AE, DAE, and VAE with PyTorch; generative adversarial networks (GAN) and code

09 – AE, DAE, and VAE with PyTorch; generative adversarial networks (GAN) and code Alfredo Canziani (冷在)

18K views - 5 years ago

08 – From LV-EBM to target prop to (vanilla, denoising, contractive, variational) autoencoder

08 – From LV-EBM to target prop to (vanilla, denoising, contractive, variational) autoencoder Alfredo Canziani (冷在)

8.5K views - 5 years ago

07 – Unsupervised learning: autoencoding the targets

07 – Unsupervised learning: autoencoding the targets Alfredo Canziani (冷在)

8.1K views - 5 years ago

01 – History and resources

01 – History and resources Alfredo Canziani (冷在)

120K views - 5 years ago

Behind the scenes

Behind the scenes Alfredo Canziani (冷在)

1.5K views - 5 years ago

06 – Latent Variable Energy Based Models (LV-EBMs), training

06 – Latent Variable Energy Based Models (LV-EBMs), training Alfredo Canziani (冷在)

10K views - 5 years ago

05.2 – But what are these EBMs used for?

05.2 – But what are these EBMs used for? Alfredo Canziani (冷在)

10K views - 5 years ago

05.1 – Latent Variable Energy Based Models (LV-EBMs), inference

05.1 – Latent Variable Energy Based Models (LV-EBMs), inference Alfredo Canziani (冷在)

18K views - 5 years ago

04.2 – Recurrent neural networks, vanilla and gated (LSTM)

04.2 – Recurrent neural networks, vanilla and gated (LSTM) Alfredo Canziani (冷在)

23K views - 5 years ago

04.1 – Natural signals properties and the convolution

04.1 – Natural signals properties and the convolution Alfredo Canziani (冷在)

16K views - 5 years ago

02 – Neural nets: rotation and squashing

02 – Neural nets: rotation and squashing Alfredo Canziani (冷在)

34K views - 5 years ago

03 – Tools, classification with neural nets, PyTorch implementation

03 – Tools, classification with neural nets, PyTorch implementation Alfredo Canziani (冷在)

24K views - 5 years ago

Supervised and self-supervised transfer learning (with PyTorch Lightning)

Supervised and self-supervised transfer learning (with PyTorch Lightning) Alfredo Canziani (冷在)

14K views - 5 years ago

Week 15 – Practicum part B: Training latent variable energy based models (EBMs)

Week 15 – Practicum part B: Training latent variable energy based models (EBMs) Alfredo Canziani (冷在)

4.2K views - 5 years ago

Week 15 – Practicum part A: Inference for latent variable energy based models (EBMs)

Week 15 – Practicum part A: Inference for latent variable energy based models (EBMs) Alfredo Canziani (冷在)

4.9K views - 5 years ago