All topics / superconvergence
Topic
You are reading the free Skim layer. Read unlocks the synthesis and sources.
Superconvergence
A training method that uses higher learning rates to achieve faster training and better generalization.
1
episodes
1
thinkers
2h
of conversation
12
books & papers
3
terms defined
The neighbourhood: superconvergence and the ideas it travels with. Drag to roam, click a star for the episode, click a neighbour to travel.
Drag to roam · scroll to zoom · click a neighbour to travel · click a star for the episode
From foundational to frontier
Climb the spectrum. The most accessible conversations come first.
Start here
ACCESSIBLECOREFRONTIER
The lexicon
Every term the guests lean on, in plain language. Read one in full, or filter to find it.
What the corpus says
The throughline across every conversation that touches this idea.
Fast.ai offers free, practical deep learning courses that emphasize accessibility and minimal BS.
Jeremy Howard · Jeremy Howard: fast.ai Deep Learning Courses and Research
Jeremy Howard argues that most deep learning research is a waste of time, advocating for practical problem-solving instead.
Jeremy Howard · Jeremy Howard: fast.ai Deep Learning Courses and Research
Howard claims that large datasets like ImageNet aren't necessary for breakthroughs; smaller datasets can be equally effective.
Jeremy Howard · Jeremy Howard: fast.ai Deep Learning Courses and Research
Transfer learning can achieve state-of-the-art results with significantly less data, challenging the notion that more data is always better.
Jeremy Howard · Jeremy Howard: fast.ai Deep Learning Courses and Research
Superconvergence allows networks to be trained ten times faster, improving both speed and generalization.
Jeremy Howard · Jeremy Howard: fast.ai Deep Learning Courses and Research
Go read
12 books and papers cited across these episodes.
For the specialist
What experts find new
3 expert-level takeaways for a specialist reader.
At the frontier
Still unresolved
1 open questions flagged across these conversations.
The thinkers
Who takes this idea on, by how often they return to it.