Published inTowards Data Sciencepytorch-widedeep, deep learning for tabular data IV: Deep Learning vs LightGBMJun 13, 2021Jun 13, 2021
Published inTowards Data Sciencepytorch-widedeep: deep learning for tabular dataA flexible package to combine tabular data with text and imagesFeb 22, 20212Feb 22, 20212
Published inTowards Data ScienceRecoTour III: Variational Autoencoders for Collaborative Filtering with Mxnet and PytorchA deep dive into the use of Variational Autoencoders for Collaborative FilteringJun 19, 2020Jun 19, 2020
Published inTowards Data SciencePredicting Amazon review scores using Hierarchical Attention Networks with PyTorch and Apache…Using the hierarchical structure of documents and MLP-based attention mechanisms to predict amazon reviews scoresJan 4, 2020Jan 4, 2020
Published inTowards Data ScienceLightGBM with the Focal Loss for imbalanced datasetsThe Focal loss (hereafter FL) was introduced by Tsung-Yi Lin et al., in their 2018 paper “Focal Loss for Dense Object Detection”[1]. It is…Oct 6, 20193Oct 6, 20193
Published inTowards Data ScienceRecoTour II: neural recommendation algorithmsAdding Deep Learning-based recommendation algorithms to RecoTour, a tour through recommendation algorithms in python.Sep 11, 20192Sep 11, 20192
Published inTowards Data SciencePutting ML in production II: logging and monitoringCombining MLflow and hyperparameter optimization tools to log and monitor all the useful data from ML pipelinesMar 11, 20193Mar 11, 20193
Published inTowards Data SciencePutting ML in production I: using Apache Kafka in Python.Using a message broker to productionise algorithms in real timeMar 5, 20191Mar 5, 20191
Published inDataDrivenInvestorRecoTour: a tour through recommendation algorithms in pythonA while ago a friend of mine asked me about approaches that would be useful when optimising GBMs. I had been asked this question a few…Nov 29, 2018Nov 29, 2018