camilogutierrez/AppliedDeepLearningClass

Class Applied Deep Learning - Summer 2018

Applied Deep Learning Class

Uniandes - Summer 2018

The use of statistical models in computer algorithms allows computers to make decisions and predictions, and to perform tasks that traditionally require human cognitive abilities. Deep learning is the interdisciplinary field at the intersection of statistics and computer science which develops such algorithnms and interweaves them with computer systems. It underpins many modern technologies, such as speech recognition, internet search, bioinformatics, computer vision, Amazon’s recommender system, Google’s driverless car and the most recent imaging systems for cancer diagnosis are all based on Deep Learning technology.

This course on Deep Learning will explain how to build systems that learn and adapt using real-world applications. Some of the topics to be covered include deep learning frameworks, convolutional neural networks, generative models nadrecurrent models. The course will be project-oriented, with emphasis placed on writing software implementations of learning algorithms applied to real-world problems, in particular, image analysis, image captioning, natural language pocessing, sentiment detection, among others.

Instructors:

• Dr. Alejandro Correa Bahnsen http://albahnsen.com
• Prof. Dr. Fabio Gonzalez http://dis.unal.edu.co/~fgonza/

Graduate assistant:

• Sergio Angulo sa.angulo@uniandes.edu.co

Resources

• [Goodfellow16] Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning (Vol. 1). Cambridge: MIT press.
• Fabio González, Machine Learning, 2018-1, Universidad Nacional de Colombia
• Fabio González, Deep Learning for Text Analysis and Understanding , Fall 2017, University of Houston
• Fabio González, Representation Learning and Deep Learning Tutorial, 2016, Univ. Politécnica de Valencia

Schedule

Introduction to Machine Learning and Neural Networks

Date	Session	Notebooks/Presentations	Exercises
June-6	Introduction to python and ML	1 - Intro to ML 2 - Intro to Python for data analysis 3 - Linear Regression 4 - Logistic Regression	E1 - Python&Pandas E2 - Regression
June-8	Machine learning systems	5 - Data preparation and model evaluation 6 - Sampling 7 - Ensemble methods 8 - Model deployment	E3 - Cross Validation E4 - Sampling and Ensembles Project1 - Kaggle
June-20	Neural networks basics	9 - Intro to NN 10 - Perceptron Training 11 - NN in Keras	E5 - Neural Networks

Introduction to Deep Learning

Date	Session	Notebooks/Presentations	Exercises
June-22	Introduction to deep learning and applications	12 - Intro to Deep Learning
July-4	Deep learning frameworks	13 - Intro to TensorFlow 14 - Deep Learning Frameworks	E6 - TensorFlow and Keras

Deep Learning for Image Analysis

Date	Session	Notebook	Exercises
July-5	Deep learning for image analyssis & CNN	15 - CNN training in Keras	P2 - Image Classification with CNN
July-6	CNN and transfer learning	16 - Convolutional Neural Networks 17 - Transfer Learning	E7 - Image Captioning
July-11	Generative models	18 - Generative Adversarial Networks

Deep Learning for Text Analysis

Date	Session	Notebook	Exercises
July-12	Intro to NLP & Intro to RNN	19 - Intro to Natural Language Processing	E8 - Sentiment Classification
July-13	Word2vec & RNN for text analysis	20 - Recurrent Neural Network and LSTM 21 - Word2Vec	E9 - Sequance Classification using LSTM

Final Project

Date	Session	Readme	Kaggle
July-23	Final project presentations	Description	Link Kaggle