OpenAI and Google just dropped latest updates on their respective AI initiatives, and I'm impressed. Time to dust off the blog and jot down what exactly is impressive about some of those, from the perspective of someone who attempted to do all of it
Blog Posts
OpenAI and Google just dropped latest updates on their respective AI initiatives, and I'm impressed. Time to dust off the blog and jot down what exactly is impressive about some of those, from the perspective of someone who attempted to do all of it
As a fun weekend side project that I haven't done in a while - I decided to do a little experiment with Salesforce Codegen model.
As some of us probably heard of the buzz around "micro frontend" recently, some even went as far as calling it "the future of the web" (I kid you not), that I have to come out and state my viewpoint of it all: it is utter garbage.
Have you ever wondered how you could build your own Google Image Search? This tutorial will walk you through so you can build your own in 15 minutes.
The Cloud Native Computing Foundation (or CNCF) offers 2 Kubernetes (or k8s - as in 8 characters between k and s) exam certifications - The CKA and CKAD exams. After taking the CKAD exam, I feel like there are several personal tips I can share, in addition to the various tips by others you can easily find online.
The 3D Photo effect - popularized by Facebook, is immensly satisfying to look at. It can make for pretty parallax-like background effects, and it can be partially replicated in 10 minutes with just a few easy steps!
In this tutorial I will briefly walk through how you can create an OpenAI Gym environment for the Google Chrome Dino game, and use Stable Baselines to quickly train an agent for it. Bonus: The environment can be easily extended to other browser games as well!.
This part is, in fact, a continuation of the previous part - still about sentence-level representations. However, I will discuss on what has been the state-of-the-art architecture for the last few years - Transformers.
In the last part I talked about various ways of representing word as vectors in NLP. However, most state-of-the-art models (as of 2020 anyway) do not even care about word vectors at all! So what happened?
In this article, I will outline through some of the most popular breakthroughs in AI in a semi-chronological order, with hope to inspire people on diving in deeper and experiment more, maybe even revisit old techniques and apply on top of newer architectures.
Stay tuned for more updates, and have a nice day!