Why Neural Networks

This repository contains all the supporting material for the talk made at Apache Spark and More Milano The slides are interactive and can be run during the presentation.

Setup

1. setup anaconda or miniconda
2. create a virtual environment

# please use python 3 :)
$conda create --name dl python=3.6

#activate the environment
source activate dl

3. install the needed libraries

$pip install -r requirements.txt

4. Install RISE from conda forge

$conda install -c conda-forge rise

4. run the jupyter notebook service

$ jupyter notebook

If you want to get more information about anaconda and jupyter check the presentation + tutorials made for the School of Artificial Intelligence at PiCampus.

Reference and Interesting Links

Suggested Books

1. Manning: Deep Learning with Python: really good for a high level introduction of arguments and ideas
2. Deep Learning: very good for a deep down
3. Elements of Statistical Learning
4. Machine Learning: A Probabilistic Perspective

MOOC

1. coursera deep learning specialization
2. MIT intro to deep learning
3. Intro to TensorFlow for Deep Learning byTensorFlow
4. Intro to Deep Learning with PyTorch byFacebook AI

Pretrained Models

1. model zoo
2. tensorflow-hub
3. tensorflow models
4. papers with code

libraries

1. keras
2. tensorflow
3. pytorch

Bonus

In the data folder there is a dataset that you can use as exercise ;)