Published inTowards Data ScienceGPT-3, a Giant Step for Deep Learning And NLPCan intelligence emerge simply by training a big enough LM using lots of data? OpenAI tries to do so, using 175 billion parametersJun 3, 20201Jun 3, 20201
Published inTowards Data ScienceThe accessibility of GPT-2 — text generation and fine-tuningText generation using GPT-2 is quite easy, using the right tools. Learn how to do it, as well as how to fine-tune the model on your own…Nov 28, 20191Nov 28, 20191
Published inTowards Data ScienceMixture of Variational Autoencoders — a Fusion Between MoE and VAEAn unsupervised approach to digit classification and generationApr 1, 20193Apr 1, 20193
Published inTowards Data ScienceTensorFlow — The Scope of Software EngineeringHow to structure your TensorFlow graph like a software engineerFeb 5, 2019Feb 5, 2019
Published inTowards Data SciencePreparing for the UnexpectedHow to apply your model to input it has never seen beforeJan 27, 2019Jan 27, 2019
Published inTowards Data ScienceThink your Data DifferentLearn how node2vec works, and what kind of information it captures that word2vec doesn’t — includes case studyJan 21, 2019Jan 21, 2019
Published inThe StartupHow to Build Your Personal Brand as a Data ScientistA couple of months ago I embarked on a journey to build my personal brand as a data scientist, and I want to share how I did it with you.Dec 31, 20186Dec 31, 20186
Published inTowards Data ScienceThe Story of a Bad Train-Test SplitSplitting your dataset to train-test sets can sometimes be more complicated than one might expectDec 16, 20181Dec 16, 20181
Published inTowards Data ScienceTensorFlow Filesystem — Access Tensors DifferentlyThe weird (but cool) way to access a tensorflow model by mounting it into a filesystemDec 9, 20182Dec 9, 20182
Published inTowards Data ScienceVariational Autoencoders Explained in DetailLearn all the details needed to implement a variational autoencoder, code included.Nov 11, 2018Nov 11, 2018