ULMFiT, every mention
9 scenes · ← back to ULMFiT
tap a year for its mentions
every year anyone Jeremy Howard 9
Verbatim, from the transcripts: the passages where ULMFiT comes up
Answer.ai & AI Magic with Jeremy Howard
- ▶ 1:09 Jeremy Howard Um, I think people are starting to understand that treating the three ULM fit steps of, like, pre-training, you know, and then the kind of, like, what people now call instruction tuning, and then, I don't know if we've got a general term…
Breaking down the OG GPT Paper by Alec Radford
- ▶ 8:59 unnamed speaker The second approach is like to use a specific recipe or schema to do transfer learning, and a very popular example of this is ULM Fit by Jeremy Howard and Sebastian Ruder, and we're going to cover this in the next two slides, I think. 4 times in the scene
- ▶ 16:10 unnamed speaker So, uh, now we have discussed ULM FED and GPT. 2 times in the scene
The End of Finetuning — with Jeremy Howard of Fast.ai
- ▶ 5:48 unnamed speaker Um, and even, yeah, talking about deep learning, you created, published a paper on ULM fit.
- ▶ 15:32 Jeremy Howard And, um, at the time, I didn't know Alec, but, um, I, after we had both, after I'd released ULM Fit 2 times in the scene
- ▶ 17:55 unnamed speaker He said, inspired by Cove, Elmo, and Yola, I'm fit. 4 times in the scene
- ▶ 32:29 Jeremy Howard So I think I've only ever done three first-person papers in my life, you know, and they were, and none of those are the ones I wanted to do, you know, they were all ones that, like, so one was ULM fit, where Sebastian Ruder reached out to… 2 times in the scene
- ▶ 39:19 Jeremy Howard I hadn't seen it before, but I'd been kind of like, as I say, I, you know, I kept working on them for a couple of years after ULM fit, and then I kind of moved on to other things, partly out of frustration, so I hadn't been fine-tuning,… 3 times in the scene
- ▶ 46:32 Jeremy Howard that's now my view, is I think ULM fit is the wrong approach, um, and that's why we're seeing a lot of these, uh,