Deep Learning for Beginners

This paper summarizes resources for deep learning for beginners.

Basic Knowledge

• What’s the Difference Between Deep Learning Training and Inference?
• How to Configure the Learning Rate When Training Deep Learning Neural Networks

Your First Experience

MNIST Example

MNIST dataset is probably the most popular for creating the first CNN example. It consists of 70,000 images of handwritten digits from 0-9.

Depending on your preference of the programming languages, there are Python and Matlab examples available.

• Python: Building a Convolutional Neural Network (CNN) in Keras. Pleaes also check Simple MNIST convnet. You need to properly install software and configure your environments.
• Matlab: Create Simple Deep Learning Network for Classification. The Matlab Deep Learning Toolbox needs to be installed before you run the example.

What is Convolutional Neural Networks (CNN)

• A Comprehensive Guide to Convolutional Neural Networks
• Matlab, Explanation of Different Layers of Convolutional Neural Networks

Deep Learning Architectures

• Deep learning architectures (IBM blog, 2017)

  This article classifies deep learning architectures into supervised and unsupervised learning and introduces several popular deep learning architectures: convolutional neural networks, recurrent neural networks (RNNs), long short-term memory/gated recurrent unit (GRU), self-organizing map (SOM), autoencoders (AE) and restricted Boltzman machine (RBM). It also gives an overview of deep belief networks (DBN) and deep stacking networks (DSNs)

• Illustrated: 10 CNN Architectures: LeNet-5, AlexNet, VGG-16, Inception-v1, Inception-v3, ResNet-50, Xception, Inception-v4, Inception-ResNets, ResNeXt-50
• Understanding AlexNet

Code Examples

TensorFlow + Keras

• Getting started with the Keras Sequential model
• Simple MNIST convnet
• Your First Deep Learning Project in Python with Keras Step-By-Step
• Keras Code examples
• How to Develop 1D Convolutional Neural Network Models for Human Activity Recognition
• Implementing AlexNet CNN Architecture Using TensorFlow 2.0+ and Keras
• Building Autoencoders in Keras

Pytorch

• Deep Learning with PyTorch: A 60 Minute Blitz

Matlab

• Matlab, Training a Model from Scratch

Online Resources

• CS231n: Convolutional Neural Networks for Visual Recognition at Stanford University link
• A summary of resources link
• Book Dive into Deep Learning

Matlab Resources

Matlab has provided lots of useful resources.

• Set Up Parameters and Train Convolutional Neural Network
• Deep Learning Tips and Tricks
• Data Sets for Deep Learning
• Matlab, Explanation of Different Layers of Convolutional Neural Networks

Development Tool

Python

• Anaconda Distribution

Code Snippet

• Check the installed packages

  conda list
  

• Install a particular tensorflow version using conda

  conda install -c conda-forge tensorflow=1.13