
154 - Just Tweak Some Parameters
Not So Standard Deviations
00:00
Neural Networks - Is There a Word for It?
I think in general there's just not a lot of combined experience for like every application. Maybe you should write a paper on designing experiments for choosing for tuning a neural network I would have to like figure out how to do that though Yeah, but that'll be helpful for what you're doing. But it feels like you know statisticians are good at designing Experiments to like hold things constant test across a whole bunch of different parameters. It's a nice application for you know experimental design for tuning. So anything regarding the data and anything regarding the model could affect the outcome right outcome being like some metricRight? Like a root means greater or right Right, and so and then then I
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.