All topics / training objectives
Topic
You are reading the free Skim layer. Read unlocks the synthesis and sources.
Training objectives
1
episodes
1
thinkers
1h
of conversation
1
books & papers
2
terms defined
The neighbourhood: training objectives 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.
Yoshua Bengio argues that neural networks struggle with credit assignment over long durations, unlike biological systems.
Yoshua Bengio · Yoshua Bengio: Deep Learning
Bengio believes that increasing neural network depth won't solve representational issues; new training objectives are needed.
Yoshua Bengio · Yoshua Bengio: Deep Learning
AI generalization is limited compared to human ability to identify principles across different contexts.
Yoshua Bengio · Yoshua Bengio: Deep Learning
Bengio sees GANs and reinforcement learning as crucial for AI's future, with model-based approaches improving generalization.
Yoshua Bengio · Yoshua Bengio: Deep Learning
Voices on training objectives
2 standout quotes from across the corpus.
Go read
1 books and papers cited across these episodes.
For the specialist
What experts find new
2 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.