Applied Machine Learning - Week 3

Monday 6th of May (afternoon):
Lectures: An introduction to Convolutional Neural Networks.
     Very cool visualisation of how a CNN works on your handwritten numbers.
     For calculating the output size of convolutional outputs, use the ConvNet Calculator.
     Potentially also: The ImageNet Competition - a revolution in ML.
     For reference: Recording of 2021 CNN lecture video (112 MB).

Exercise: The exercise is to recognise handwritten numbers with a Convolutional Neural Network: CNN_MNISTdata.ipynb.
     If you want a step up in complexity, consider classifying volcanic ash (socalled 'tephra") from Greenlandic ice cores, based on images of the tephra.

Wednesday 8th of May (morning):
Lectures: Analysing geometric data using Graph Neural Networks.
     For reference: Recording of 2021 lecture (78 MB).

Exercise: The exercise is to classify which molecules (which can be represented by a graph) are potentially HIV inhibiting.

Wednesday 8th of May (afternoon):
Lectures: Time series, Natural Language Processing (NLP), and Transformers.
     For reference: Recording of 2021 RNN/LSTM lecture video (222 MB).

Exercise: First, consider the simple example LSTM making FlightPassengerPredictions.ipynb on 1949-1961 airline data.
     Then, use an LSTM to do Natural Language Processing, in this case estimate if a review was good or bad based on IMDB data.

Last updated: 4th of May 2024 by Troels Petersen.