Transformers Explained Visually - Multi-head Attention, deep dive

A Gentle Guide to the inner workings of Self-Attention, Encoder-Decoder Attention, Attention Score and Masking, in Plain English.

Read More

All Stories

Enterprise ML - Why putting your model in production takes longer than building it

A Gentle Guide to Enterprise, in Plain English

In Neural, tutorial, Jun 28, 2021

Enterprise ML - Why building and training a "real-world" model is hard

A Gentle Guide to the lifecycle of a Machine Learning project in the Enterprise, the roles involved and the challenges of building models, in Plain English

In Enterprise, Jun 16, 2021

Transformers Explained Visually - Not just how, but Why they work so well

A Gentle Guide to how the Attention Score calculations capture relationships between words in a sequence, in Plain English.

In Transformers, tutorial, Jun 02, 2021

Batch Norm Explained Visually - Why does it work?

A Gentle Guide to the reasons for the Batch Norm layer's success in making training converge faster, in Plain English

In Neural, tutorial, May 27, 2021

Differential and Adaptive Learning Rates - Neural Network Optimizers and Schedulers demystified

A Gentle Guide to boosting model training and hyperparameter tuning with Optimizers and Schedulers, in Plain English

In Neural, tutorial, May 22, 2021

Batch Norm Explained Visually — How it works, and why neural networks need it

A Gentle Guide to an all-important Deep Learning layer, in Plain English

In Neural, tutorial, May 10, 2021

Foundations of NLP Explained — Bleu Score and WER Metrics

A Gentle Guide to two essential metrics (Bleu Score and Word Error Rate) for NLP models, in Plain English

In NLP, tutorial, May 07, 2021

Image Captions with Attention in Tensorflow, Step-by-step

An end-to-end example using Encoder-Decoder with Attention in Keras and Tensorflow 2.0, in Plain English

In Vision, tutorial, Apr 27, 2021

Image Captions with Deep Learning - State-of-the-Art Architectures

A Gentle Guide to Image Feature Encoders, Sequence Decoders, Attention, and Multimodal Architectures, in Plain English

In Vision, tutorial, Apr 20, 2021

Leveraging GeoLocation Data with Machine Learning - Essential Techniques

A Gentle Guide to Feature Engineering and Visualization with Geolocation Data, in Plain English

In GeoLocation, tutorial, Apr 11, 2021