This paper summarizes resources for deep learning for beginners.
First CNN Example
MNIST dataset is probably the most popular for create 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. If you are using Python, 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.
Convolutional Neural Networks (CNN)
What is Convolutional Neural Networks (CNN)
- A Comprehensive Guide to Convolutional Neural Networks
- Matlab, Explanation of Different Layers of Convolutional Neural Networks
- Your First Deep Learning Project in Python with Keras Step-By-Step
- How to Develop 1D Convolutional Neural Network Models for Human Activity Recognition
Common CNN Architecture
- Illustrated: 10 CNN Architectures: LeNet-5, AlexNet, VGG-16, Inception-v1, Inception-v3, ResNet-50, Xception, Inception-v4, Inception-ResNets, ResNeXt-50
Few Shot Learning
- An Introduction to Few-Shot Learning
- Understanding Few-Shot Learning in Computer Vision – What You Need to Know
Anaconda Distribution is strongly recommended.
- Check the installed packages
- Install a particular tensorflow version using conda
conda install -c conda-forge tensorflow=1.13
Deep Learning Tutorials
- CS231n: Convolutional Neural Networks for Visual Recognition at Stanford University link
- A summary of resources link
- Book Dive into Deep Learning
Matlab has provided lots of useful resources.