On a similar note, I really hope that the AI companies that don't make it, but have invested a lot in curating and annotating high quality datasets, would release them to the public. Autonomous car and robotics companies in particular since that kind of data doesn't exist on the internet as abundantly as, say, natural language text.
If you want to gain familiarity with the kind of terminology you mentioned here, but don't have a background in graduate-level mathematics (or even undergrad really), I highly recommend Andrew Ng's "Deep Learning Specialization" course on Coursera. It was made a few years ago but all of the fundamental concepts are still relevant today.
Fei Fei Li and Andrej Karpathy's Stanford CS231N course is also a great intro to the basic of the math from an engineering forward perspective. I'm pretty sure all the materials are online. You build up from the basic components to an image focused CNN.
Interesting! I would like to learn more about how AI is being applied to robotics. Do you have any suggestions for how to keep up with developments/ideas in this field?
..and plan to do an updated version soon for much of what's been released since. I've also done work related to LLM and robotics integration, also on that site.
Working my way through your blog post and it is so refreshing. Unfortunately my algorithm currently is showing me takes which are extreme on either end (like in your blog post).
> Technology’s largest leaps occur when new tools are provided to those that want to make things.
I love this sentence. And the general attitude of curiosity of your post.
Thanks! Appreciate the kind words. I should have in the next month or so (interviewing and finishing my Master's, so there's been delays) a follow up that follows more advancements in the router style VLA, sensoiromotor VLM, and advances in embedding enriched vision models in general.
If you want a great overview of what a modern robotics stack would look like with all this, https://ok-robot.github.io/ was really good and will likely make it into the article. It's a VLA combined with existing RL methods to demonstrate multi-tasking robots, and serves as a great glimpes into what a lot of researchers are working on. You won't see these techniques in robots in industrial or commercial settings - we're still too new at this to be reliable or capable enough to deploy these on real tasks.
Thanks! So this is something I tried and qualitatively I didn't see a huge difference. I'd like to swap out my hand rolled modules with standard pytorch modules for self attention etc. and train it on the wikipedia English split. That's on my to-do list for sure.
I run some tests. Single model of the same size is better than MoE. Single expert out of N is better than model of the same size (i.e. same as expert). 2 experts are better than one. That was on small LLM, not sure if it scales.
Then perhaps a method emerges out of this to make training faster (but not inference) - do early training on highly quantized (even ternary) weights, and then swap out the weights for fp16 or something and fine-tune? Might save $$$ in training large models.
Because it shifts the burden (or at least appearance) of responsibility from those experiencing homelessness to the government orgs tasked with housing them.
Uh... how does "unhoused" do that? Or, I don't see how unhoused is synonymous with "the government has not provided these people with a house". The opposite of unhoused would be housed. Is everyone that is housed in that position because the government provided a house for them?
Wrongly so I’d argue. It’s your own responsibility to secure a place for yourself (to live, and in society generally). Failure to do this is personal, not collective.
