Course Code: appaided
Duration: 21 hours
Prerequisites:

-

Overview:

-

Course Outline:

Plan Szkolenia

Supervised learning: classification and regression

Bias-variance trade off

Logistic regression as a classifier

Measuring model performance 

Support vector machines

Decision trees

Clustering and unsupervised learning: dimensionality reduction

K-means clustering

PCA

Autoencoders    

Advanced neural network architectures

Recurrent neural networks for time-structured data

LSTM

Practical examples of problems that AI can solve:

Image analysis

Forecasting financial/time series

Natural language processing

Recommender systems    

Software platforms used for AI applications:

Numpy, Pandas, TensorFlow, Keras, Spark MLlib

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

Deployment of ML models