Table of Content
- General Machine Learning
- Deep Learning
- Different Machine Learning Tasks
- Deep Learning – Some State-of-The-Art Publications
I will add more information related to AI especially Deep Neural Networks from time to time.
This is a summary of some of the resources that I have either found useful myself or heard people.
General Machine Learning
Classes
- Coursera’s Machine Learning Class - This Coursera class, taught by Andrew Ng
- Information Systems and Machine Learning Lab (ISMLL) at University of Hildesheim
Reading
Books
Programming
Deep Learning
Reading
- Neural Networks & Deep Learning by Michael Nielsen
- Deep Learning Book by Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016)
Programming / Frameworks
Different Machine Learning Tasks
Classification
Any classification tasks depend upon labeled datasets.
Labeled datasets are used to transfer human’s knowledge to the dataset in order for an artificial network to extract information from this dataset to learn the correlation between labels and data information.
Using labeled datasets is known as supervised learning. In the following I provide a list (without any claim to completeness) of some classification tasks:
- Detect faces, identify people in images, recognize facial expressions (angry, joyful)
- Detect differnt types of objects in images (animals, flowers, stop signs, pedestrians, lane markers, traffic lights, …)
- Recognize gestures
- Detect voices, identify speakers, transcribe speech to text, recognize sentiment in voices
- Classify text as spam (in emails), or fraudulent (in insurance claims); recognize sentiment in text (customer feedback)
Some Image-based Classification Publications
- Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
- Deep Learning using Linear Support Vector Machines
- ImageNet Classification with Deep Convolutional Neural Networks
Some Data-based Classification Publications
- Quantum support vector machine for big data classification
- Convolutional Neural Networks for Sentence Classification
Natural Language Processing
Machine Translation
Neural machine translation attempts to build and train a single, large neural network. In interference step this neural network reads a sentence and outputs a correct translation.