Christopher Thomas BSc Hons. MIAPinThought VectorLatent Diffusion and Perceptual Latent LossThis article shows a novel approach to training a generative model for image generation at reduced training times using latents and using a…9 min read·Nov 26, 2023--1--1
Christopher Thomas BSc Hons. MIAPinTowards Data ScienceSuper Resolution: Adobe Photoshop versus leading Deep Neural NetworksHow effective is Adobe’s Super Resolution compared to the leading super resolution deep neural network models? This article attempts to…19 min read·Mar 24, 2021--2--2
Christopher Thomas BSc Hons. MIAPinTowards Data ScienceSuper Convergence with Cyclical Learning Rates in TensorFlowSuper-Convergence using Cyclical Learning Rate schedules is one of the most useful techniques in deep learning and very often overlooked…9 min read·Jan 31, 2021----
Christopher Thomas BSc Hons. MIAPinTowards Data ScienceDeep learning image enhancement insights on loss function engineeringInsights on techniques and loss function engineering for Super Resolution, Colourisation, and style transfer.15 min read·Feb 21, 2020--2--2
Christopher Thomas BSc Hons. MIAPMoss House — UCB Birmingham — a £42,000,000 construction project next to residential homesMoss House is a 42 million pound demolition and construction project in a both a conservation and residential area within Birmingham’s…16 min read·Feb 2, 2020----
Christopher Thomas BSc Hons. MIAPinTowards Data ScienceTabular data analysis with deep neural netsDeep neural networks are now an effective technique for tabular data analysis, requiring little feature engineering and less maintenance…9 min read·Sep 9, 2019--1--1
Christopher Thomas BSc Hons. MIAPinTowards Data ScienceRecurrent Neural Networks and Natural Language Processing.Recurrent Neural Networks (RNNs) are a form of machine learning algorithm that are ideal for sequential data such as text, time series…10 min read·Jun 9, 2019----
Christopher Thomas BSc Hons. MIAPinTowards Data ScienceAn introduction to Convolutional Neural NetworksA Convolutional neural network (CNN) is a neural network that has one or more convolutional layers and are used mainly for image…10 min read·May 27, 2019--3--3
Christopher Thomas BSc Hons. MIAPinTowards Data ScienceThe basics of Deep Neural NetworksWith the rise of libraries such as Tensorflow 2.0 and Fastai, implementing deep learning has become accessible to so many more people and…8 min read·May 12, 2019----
Christopher Thomas BSc Hons. MIAPinTowards Data ScienceU-Net deep learning colourisation of greyscale imagesThis article describes experiments training a neural network to generate 3 channel colour images from single channel greyscale images…11 min read·Mar 14, 2019--2--2