Articles & Research

Multivariate Temporal Autoencoder for Predictive Reconstruction of Deep Sequences

Jakob Aungiers
28th September 2020

A multi-branch deep neural network approach to tackling the problem of multivariate temporal sequence prediction by modelling a latent state vector representation of data windows through the use of a recurrent autoencoder and predictive model.

AI Security - Neural Network Backdoors

Jakob Aungiers
1st October 2018

AI models are increasingly being used in complex security and access related applications. The security implications of these models is often not known. Here we demonstrate two different attack vectors deep neural networks are prone to.

Time Series Prediction Using LSTM Deep Neural Networks

Jakob Aungiers
1st September 2018

This article focuses on using an LSTM neural network architecture to provide time series forecasting using Keras and Tensorflow – specifically on stock market datasets to provide momentum indicators of stock price.

How to Develop an AI Trading Strategy System

Jakob Aungiers
29th March 2018

There was a time when trading strategies were abundant and easy to find. Unfortunately today's landscape is considerably different, with a lot of misconceptions on what makes a successful AI systematic trading strategy.

Getting Started with Deep Learning and the Altum Platform

Jakob Aungiers
29th March 2018

This article will help you get to grips with the basics of the Altum Platform and will guide you step-by-step to creating, training and running your first deep learning model.