• Stars
    star
    185
  • Rank 201,670 (Top 5 %)
  • Language
    Jupyter Notebook
  • Created about 6 years ago
  • Updated 5 months ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Material del curso de Deep Learning de la Universidad de Chile

CC6204 Deep Learning

Curso introductorio (en espa帽ol) al 谩rea de aprendizaje basado en redes neuronales profundas, com煤nmente conocida como Deep Learning. Durante el curso aprender谩n la teor铆a detr谩s de los modelos de Deep Learning, su funcionamiento y usos posibles. Ser谩n capaces de construir y entrenar modelos para resolver problemas reales.

Primavera 2020

Requerimientos

Organizaci贸n del Curso

1. Fundamentos

Introducci贸n, IA vs ML vs DL, 驴Por qu茅 DL ahora? (video)

1.1. Redes neuronales modernas

  • Perceptr贸n, funciones de activaci贸n, y representaci贸n matricial (video)
  • UAT, Redes Feed-Forward, y funci贸n de salida (softmax) (video)
  • Descenso de Gradiente para encontrar los par谩metros de una red (video)
  • Grafos de computaci贸n y el algoritmo de BackPropagation (video1, video2)
  • Tensores, Notaci贸n de Einstein, y Regla de la Cadena Tensorial (video)
  • Entrop铆a Cruzada y Backpropagation a mano con Tensores (video)
  • Aspectos pr谩cticos de entrenamiento y Red FF a mano en pytorch (video)

Readings: Chapter 2. Lineal Algebra, Chapter 3. Probability and Information Theory, Chapter 6. Deep Feedforward Networks

1.2. Inicializaci贸n, Regularizaci贸n y Optimizaci贸n

  • Generalizaci贸n, Test-Dev-Train set y Regularizaci贸n (video)
  • Ensemble, Dropout, y Desvanecimiento de Gradiente (video)
  • Inicializaci贸n de par谩metros y Normalizaci贸n (video)
  • Algoritmos de Optimizaci贸n, SGD con Momentum, RMSProp, Adam (video)

Readings: Chapter 7. Regularization for Deep Learning, Chapter 8. Optimization for Training DeepModels, Chapter 11. Practical Methodology

2. Redes Neuronales Convolucionales (CNN)

  • Introducci贸n a Redes Convolucionales (video)
  • Arquitecturas m谩s conocidas: AlexNet, VGG, GoogLeNet, ResNet, DenseNet (video1, video2, video3)

Readings: Chapter 9. Convolutional Networks, Chapter 12. Applications

3. Redes Neuronales Recurrentes (RNN)

  • Introducci贸n a Redes Recurrentes (video)
  • Arquitectura de Redes Recurrentes (video)
  • Auto-regresi贸n, Language Modelling, y Arquitecturas Seq-to-Seq (video)
  • RNNs con Compuertas y Celdas de Memoria: GRU y LSTM (video)

Readings: Chapter 10. Sequence Modeling: Recurrentand Recursive Nets, Chapter 12. Applications

4. T贸picos avanzados

  • Atenci贸n Neuronal (video)
  • Transformers (video)
  • Variational Autoencoders
  • Generative Adversarial Networks
  • Neural Turing Machine (NeuralTM)
  • Differentiable Neural Computers (DNC)

Readings: Chapter 14. Autoencoders, Chapter 20. Deep Generative Models

Libros

No hay ning煤n libro de texto obligatorio para el curso. Algunas conferencias incluir谩n lecturas sugeridas de "Deep Learning" de Ian Goodfellow, Yoshua Bengio, and Aaron Courville; sin embargo, no es necesario comprar una copia, ya que est谩 disponible de forma gratuita en l铆nea.

  1. Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (bibliograf铆a fundamental del curso)
  2. Dive into Deep Learning by Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola
  3. Deep Learning for Vision Systems by Mohamed Elgendy
  4. Probabilistic and Statistical Models for Outlier Detection by Charu Aggarwal
  5. Speech and Language Processing by Daniel Jurafsky and James Martin
  6. Notes on Deep Learning for NLP by Antoine J.-P. Tixier
  7. AutoML: Methods, Systems, Challenges edited by Frank Hutter, Lars Kotthoff, and Joaquin Vanschoren

Tutoriales

  1. Quickstart tutorial numpy
  2. DeepLearning con PyTorch en 60 minutos

Otros Cursos de DL

  1. Introduction to Deep Learning
  2. Deep learning course on Coursera by Andrew Ng
  3. CS231n course by Stanford University
  4. Courses by fast.ai

Videos

  1. Visualizing and Understanding Recurrent Networks
  2. More on Transformers: BERT and Friends by Jorge P茅rez
  3. Atenci贸n neuronal y el transformer by Jorge P茅rez

Otras Fuentes

  1. How To Improve Deep Learning Performance
  2. An Overview of ResNet and its Variants
  3. CNN Architectures: LeNet, AlexNet, VGG, GoogLeNet, ResNet and more
  4. Understanding LSTM Networks
  5. Attention Is All You Need
  6. Attention is all you need explained
  7. BERT exaplained

More Repositories

1

beto

BETO - Spanish version of the BERT model
479
star
2

spanish-word-embeddings

Spanish word embeddings computed with different methods and from different corpora
344
star
3

CC6205

Natural Language Processing
TeX
217
star
4

CC5205

Introducci贸n a la Miner铆a de Datos
Shell
190
star
5

wefe

WEFE: The Word Embeddings Fairness Evaluation Framework. WEFE is a framework that standardizes the bias measurement and mitigation in Word Embeddings models. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!
Python
169
star
6

CC6104

Teaching material of the course "Statistical Thinking" of the Department of Computer Science at the University of Chile.
TeX
87
star
7

lightweight-spanish-language-models

ALBETO and DistilBETO are versions of ALBERT and DistilBERT pre-trained exclusively on Spanish corpora.
Python
25
star
8

rivertext

RiverText is a framework that standardizes the Incremental Word Embeddings proposed in the state-of-art. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!
Python
18
star
9

GLUES

Resources for GLUE benchmark in Spanish
14
star
10

PracticaProfesional

Everything related to practica profesional
11
star
11

speedy-gonzales

Code for "Speedy Gonzales: A Collection of Fast Task-Specific Models for Spanish"
HTML
10
star
12

relela

Representations for Learning and Language
HTML
8
star
13

SNEC

Special Needs Education Corpus project
Jupyter Notebook
2
star
14

RiverText

Machine Learning for Text Sreams
2
star
15

word-embeddings-benchmarks

Python
1
star