Machine Learning in Finance
Code
400103
Academic unit
NOVA Information Management School
Credits
7.5
Teacher in charge
Mauro Castelli
Teaching language
Portuguese. If there are Erasmus students, classes will be taught in English
Objectives
- Understand the design principles of neural networks;
- Understand the concept of activation function;
- Understand the backpropagation algorithm for training a neural network;
- Being able to build a neural network to solve classification tasks;
- Being able to use Keras or similar libraries to build a Neural Network;
- Understand the convolution operator and the idea behind convolutional neural network;
- Understand the main principles of recurrent neural network;
- Understand LSTM and how they can be applied to counteract vanishing gradient problem.
- Being able to apply one of the deep model presented to solve financial classification or regression tasks.
Prerequisites
N/A
Subject matter
Single perceptron and the training process;
Neural Networks with hidden layers and the backpropagation algorithm;
Convolutional Neural Networks;
Applicatio of CNN to image analysis;
Recurrent Neural Networks;
Vanishing gradient and LSTM
Application of LSTM to time series analysis
Bibliography
Deep Learning. Ian Goodfellow, Yoshua Bengio, Aaron Courville. MIT Press, 2016.
Teaching method
Theoretical and practical classes.
Evaluation method
First epoch: project with discussion.
Second epoch: project with discussion.