As discussed in the previous step, time series data are ubiquitous in financial applications. In this article, we introduce a Recurrent Neural Network (RNN), which has strength for time series …
Welcome to Week 4 – the last week of our course! This week, we will discuss recurrent neural networks (RNNs) and uncover their mathematical foundation. In this video, Professor Hao …
First of all, we would thank all registered users for your participation. Your involvement is an important and integral part of this course. We will update the course based on …
The four-week introductory course has now come to an end. We hope that it can help you build up a theoretical understanding of deep learning and acquire hands-on experience in …
Tensorflow has implemented many commonly-used RNN layers, including basic RNN, GRU, LSTM, etc. To construct a multi-layer RNN in Tensorflow, one simply stacks individual layers by sequentially adding each layer …
In this video, Hao introduces Backpropagation through time, an efficient algorithm to compute the gradients of RNNs, and explains the step-by-step derivation. Similar to DNNs, RNNs training is conducted by …
In Step 4.3, we discussed the motivation of the RNNs for time series data modelling. In this article, I introduce the mathematical formulation of RNN network architecture. RNN proposes a …
In Step 3.9, you learn three gradient descent-based methods for optimising model parameters in supervised learning. Hence for training a deep neural network, the problem boils down to how to …
In Step 3.8, we introduced the gradient descent method, which is a general numerical method for optimization. In this video, Dr Alex Tse explains how to apply gradient-descent algorithms to …
In Step 3.4, we introduce the shallow neural network. In this video, Dr Alex Tse introduces Deep neural networks (DNNs). DNNs can be regarded as the extension of the shallow …
You may wonder why neural networks are so powerful and seem to successfully solve a wide range of data challenges like a panacea. One mathematical justification may lie in the …
Shallow neural network is the simpliest neural network architecture as shown in the below figure. We introduce the mathematical formulation of shallow neural network architecture and in particular, explain the …
Welcome to Week 3! This week, we will dive into deep neural networks (DNNs) and uncover the mathematics behind powerful DNNs. In this video, Professor Hao Ni summarizes the learning …
Quants, as the name shows, need to grasp solid quantitative skills. No matter which side of the industry (buy or sell side) she wishes to work in, common skills include …
Challenges of ML in Quantitative Finance Unique characteristics of financial data impose great challenges in the applications of machine learning. Low signal-to-noise ratio. Financial markets are highly uncertain, and the …