- Bias-variance trade off
- Logistic regression as a classifier
- Measuring classifier performance
- Support vector machines
- Neural networks
- Random forests
- principal component analysis
- autoencoders
- convolutional neural networks for image analysis
- recurrent neural networks for time-structured data
- the long short-term memory cell
- image analysis
- forecasting complex financial series, such as stock prices,
- complex pattern recognition
- natural language processing
- recommender systems
- TensorFlow, Theano, Caffe and Keras
- AI at scale with Apache Spark: Mlib
- overfitting
- biases in observational data
- missing data
- neural network poisoning
There are no specific requirements needed to attend this course.
28 hours (usually 4 days including breaks)
