The current crop of text-to-image generators are awe-inspiring yet generic, i.e., you cannot insert your personalization into the generated image. That changed with Dreambooth. Below is a jargon-free explanation of Dreambooth usage, so you can dream up hitherto impossible use cases. We do that with our app DayDream, a lightweight…

Oh, have I got your attention now? We’re on a mission to retire the phrase RTFM and coin something new; QTM (Query the Manual). For the Impatient… Arm yourself with an OpenAP key and head over to my GitHub repo and play the notebook. You should be able to reproduce my results.

The lively debate about augmenting machine Learning with symbolic processing rages on. Until we get a break-thru, we must live with tokenizing the input text and converting them into numeric identifiers (token-ids). …

Thankfully, we can derive a variety of models from the BERT architecture to fit our memory and latency needs. Turns out, model capacity (the number of parameters) is factored on three variables, the number of layers, the hidden embedding size, and the number of attention heads. This post puts the…

In many scenarios where we’re learning from a small dataset, an over-fitted model is a likely outcome. By that we mean, the model may perform OK on the training data but does not generalize very well to test data. In this post, we highlight a simple yet powerful way to…

NLP model training has achieved some degree of generalization; however, nuggets of value lie concealed in simple and affordable fine-tuning for specific tasks. A concrete example follows. Transformer based NLP are, well, transformational! There’s considerable excitement about openly available NLP models that are trained at scale on vast swaths of…

The Importance of Attention Language modeling tasks like answering questions and classifying documents are now designed with transformer networks. The attention building block is a central component of the transformer. Recently, transformer-based computer vision models have attained state-of-the-art results (further underscoring the importance of attention). …

I highlight ways to lower the barrier to entry into biomedical text processing and speed up progress in this vitally important area impacting mankind. Spotlighting the Challenge Medical documents have grown to the extent that, PubMed, the search engine and repository for biomedical research articles, adds 4,000 new papers every day and over…

Background By now you may have come across the position paper, PyTorch: An Imperative Style, High-Performance Deep Learning Library presented at the 2019 Neural Information Processing Systems. The paper promotes PyTorch as a Deep Learning framework that balances usability with pragmatic performance (sacrificing neither). Read the paper and judge for yourself. …