A tutorial on how to build a spam classifier (or any other classifier) by fine-tuning the DistilBERT model — The DistiBERT model was released by the folks at Hugging Face, as a cheaper, faster alternative to large transformer models like BERT. It was originally introduced in a blog post. The way this model works — is by using a teacher-student training approach, where the “student” model is a smaller…

Taking inspiration from the century old Gödel’s completeness theorem to define the limits of natural language processing and peer into what might the next breakthroughs be… — In the last 5 years, there have been tremendous research breakthroughs in the field of natural language processing. We are starting to reach near human level accuracy in many language tasks including question answering, summarization, dialogue, translation, etc. But what are the limits of natural language processing?

A tutorial on fine-tuning the Hugging Face RoBERTa QA Model on custom data and obtaining significant performance boosts — Question Answering and Transformers BERT is a transformer model that took the world by storm in 2019. BERT was trained on unlabeled data by masking words and training the model to predict these masked words based on context. BERT was later fine-tuned on multiple tasks and achieved state of the art performance on many…

I’m pretty sure you would not — yet, the flawed COMPAS risk score is being used all the time by U.S. courts. — I’m pretty sure you would not — yet, the flawed COMPAS risk score is being used all the time by U.S. courts. In 2015, the company Northpointe came up with a risk score to help judges in handing out sentences. The Violent Recidivism Scale is used to assess how likely…

Google’s original codebase would likely be worthless today — François Chollet — I don’t know about you — but usually when I think about breakthroughs and imagine what does it take to build something successful with the power to transform society, I think about the ‘thing’ that was built and the person (or the small group of people) who built that thing…

I recreated the Classic kids story “Going on a Bear Hunt” with illustrations completely generated by Stable Diffusion— and now you can too! — There has been a recent boom of AI tools that generate content from various prompts like text and images. Stable Diffusion is a popular tool that was released earlier this year by OpenAI and is accessible to the public! So how does Stable Diffusion work? Stable Diffusion

Intelligence is the extent to which actions are likely to achieve objectives. Hallmarks of intelligence like learning, solving problems, etc. increase the likelihood of this success — Giving credit where it is due: the profound one-line definition of intelligence: Intelligence is the extent to which actions are likely to achieve objectives is not of my own creation- but paraphrasing from Stuart Russel’s book Human Compatibility ( apparently this books rates high on Elon Musks’ list of books…

With recent AI advances where algorithms have been called sentient and can explain jokes — this article is a 30,000 foot view on the most important breakthroughs in NLP and their impacts — Grammar and Machines In 1957, a struggling linguistics graduate wrote a revolutionary book with a revolutionary premise: by understanding the rules behind grammar, it is possible to predict all grammatical sentences of any language. The author was Noam Chomsky, and the book — Syntactic Structures. …

Carnatic Music features rich recurrent patterns from a few building blocks — making it a rich playground to explore AI based music generation. Let’s see how LSTM can generate new basic compositions — Building Blocks in Carnatic Music Carnatic music is one of 2 Indian classical music forms (the other being Hindustani music). Unlike in Western classical music where compositions are set to a particular key (e.g. Beethoven’s Symphony №5 in C minor) and features multiple modes; Carnatic music compositions are mostly set to a single distinct mode…