Applied Machine Learning - Week 4

Monday 15th of May (afternoon):
Lectures: An introduction to Convolutional Neural Networks (Daniel Murnane).
     Very cool visualisation of how a CNN works on your handwritten numbers.
     For calculating the output size of convolutional outputs, use the ConvNet Calculator.
     For reference: Recording of 2021 CNN lecture video (112 MB).

Exercise: First step is to see/understand how to recognise handwritten numbers with a Convolutional Neural Network: CNN_MNISTdata.ipynb.
     The main exercise consists of classifying volcanic ash (socalled 'tephra") from Greenlandic ice cores, based on images of the tephra.
     This exercise also requires two CSV files with metadata: train and test sample.

Wednesday 17th of May (morning):
Lectures: Recurrent Neural Networks (RNN), Long Short Term Memory (LSTM) and Natural Language Processing (NLP) (Inar Timiryasov).
     For reference: Recording of 2021 RNN/LSTM lecture video (222 MB).

Exercise: First, consider the 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.

Wednesday 17th of May (afternoon):
Lectures: Auto-Encoder and anomaly detection (TP).

Exercise: The exercise is about classifying digits i.e. the MNIST data, but this time with an autoencoder in an unsupervised manner.

Last updated: 16th of May 2023 by Troels Petersen.