Course Code
appai
Duration
28 hours (usually 4 days including breaks)
Requirements
There are no specific requirements needed to attend this course.
Overview
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.
Course Outline
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
.png "new york stock exchange (nyse)")
_ireland.gif "environmental protection agency (epa) ireland")
.png "aeronautical radio, incorporated (arinc)"){kind=small}
.jpg "european organization for nuclear research (cern)")
.png "european space agency (esa)")
