this post was submitted on 09 Nov 2023
1 points (100.0% liked)

Machine Learning

1 readers
1 users here now

Community Rules:

founded 1 year ago
MODERATORS
 

I'm a data engineer who somehow ended up as a software developer. So many of my friends are working now with the OpenAI api to add generative capabilities to their product, but they lack A LOT of context when it comes to how LLMs actually works.

This is why I started writing popular-science style articles that unpack AI concepts for software developers working on real-world application. It started kind of slow, honestly I wrote a bit too "brainy" for them, but now I've found a voice that resonance with this audience much better and I want to ramp up my writing cadence.

I would love to hear your thoughts about what concepts I should write about next?
What get you excited and you find hard to explain to someone with a different background?

you are viewing a single comment's thread
view the rest of the comments
[–] rejectedlesbian@alien.top 1 points 1 year ago (4 children)

optimizer OMG no one touched optimizes for decades.
we basically figure its ADAM/SGD and there wasnt really any improvement on it.

I tried finding an improvement to it myself for a few months but failed miserably

[–] satireplusplus@alien.top 1 points 1 year ago

Because its super hard to build something that works better than ADAM across many tasks. There's probably no shortage of people trying to come up with something better.

[–] currentscurrents@alien.top 1 points 1 year ago

Learned optimizers look promising - training a neural network to train neural networks.

Unfortunately they're hard to train and nobody has gotten them to really work yet. The two main approaches are meta-training or reinforcement learning, but meta-training is very expensive and RL has all the usual pitfalls of RL.

[–] koolaidman123@alien.top 1 points 1 year ago

Nothing beats adamw + compute. Plus with the current data centric approach everything kinda converges at scale

[–] charlesGodman@alien.top 1 points 1 year ago

There has been LOADS of research on deep learning optimisation in recent years. However, TLDR nothing beats ADAM.