Applied AI from Scratch

There are no specific requirements needed to attend this course.

This is a 4 day course introducing AI and it's application. There is an option to have an additional day to undertake an AI project on completion of this course. 

Supervised learning: classification and regression

• Bias-variance trade off
• Logistic regression as a classifier
• Measuring classifier performance 
• Support vector machines
• Neural networks
• Random forests    

Unsupervised learning: clustering, anomaly detetction

• principal component analysis
• autoencoders    

Advanced neural network architectures

• convolutional neural networks for image analysis
• recurrent neural networks for time-structured data
• the long short-term memory cell

Practical examples of problems that AI can solve, e.g.

• image analysis
• forecasting complex financial series, such as stock prices,
• complex pattern recognition
• natural language processing
• recommender systems    

Software platforms used for AI applications:

• TensorFlow, Theano, Caffe and Keras
• AI at scale with Apache Spark: Mlib    

Understand limitations of AI methods: modes of failure, costs and common difficulties

• overfitting
• biases in observational data
• missing data
• neural network poisoning