All topics / deep learning
Topic
You are reading the free Skim layer. Read unlocks the synthesis and sources.
Deep learning
13
episodes
13
thinkers
20h
of conversation
40
books & papers
28
terms defined
The neighbourhood: deep learning 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.
+16 more terms unlock the full lexicon with Read.
What the corpus says
The throughline across every conversation that touches this idea.
Wojciech Zaremba suggests that AI models like GPT-3 struggle with long text coherence due to lack of feedback mechanisms.
Wojciech Zaremba · Wojciech Zaremba: OpenAI Codex, GPT-3, Robotics, and the Future of AI
Codex can democratize coding by translating natural language into code, enabling non-programmers to create software.
Wojciech Zaremba · Wojciech Zaremba: OpenAI Codex, GPT-3, Robotics, and the Future of AI
Zaremba argues that the success of deep learning hinges on the multiplicative effect of compute, algorithms, and data.
Wojciech Zaremba · Wojciech Zaremba: OpenAI Codex, GPT-3, Robotics, and the Future of AI
Robotics faces significant challenges, including high costs and latency issues, which impede real-world deployment.
Wojciech Zaremba · Wojciech Zaremba: OpenAI Codex, GPT-3, Robotics, and the Future of AI
Zaremba believes that consciousness might be a form of metacompression, linking it to memory and brain wave patterns.
Wojciech Zaremba · Wojciech Zaremba: OpenAI Codex, GPT-3, Robotics, and the Future of AI
Jitendra Malik argues that achieving 99% of a computer vision solution is exponentially harder than reaching 50%, due to complex edge cases.
Jitendra Malik · Jitendra Malik: Computer Vision
Malik believes current AI systems require far more data than humans to learn similar capabilities, highlighting inefficiencies in existing models.
Jitendra Malik · Jitendra Malik: Computer Vision
Video recognition technology is a decade behind static image processing, with action classification performance stuck at around 30%.
Jitendra Malik · Jitendra Malik: Computer Vision
Malik emphasizes the importance of segmentation in computer vision, which allows object identification without needing explicit naming.
Jitendra Malik · Jitendra Malik: Computer Vision
Biological vision systems use feedback mechanisms and shallower networks, contrasting with the deeper, feed-forward networks in artificial vision.
Jitendra Malik · Jitendra Malik: Computer Vision
Ilya Sutskever co-authored the AlexNet paper, a pivotal moment in deep learning's rise.
Ilya Sutskever · Ilya Sutskever: Deep Learning
Transformers have replaced RNNs due to their efficiency and scalability in deep learning tasks.
Ilya Sutskever · Ilya Sutskever: Deep Learning
Voices on deep learning
12 standout quotes from across the corpus.
Go read
40 books and papers cited across these episodes.
For the specialist
What experts find new
27 expert-level takeaways for a specialist reader.
At the frontier
Still unresolved
18 open questions flagged across these conversations.
The thinkers
Who takes this idea on, by how often they return to it.
FC
1
1
VV
1
DS
1
GM
1
1
JH
1
JM
1
MM
1
PN
1
RM
1
WZ
1
Francois Chollet
Noam Chomsky
Computer Scientist
Vladimir Vapnik
Mathematician
David Silver
Gary Marcus
Neuroscientist
Ilya Sutskever
Mathematician
Jeremy Howard
Jitendra Malik
Computer Scientist
Melanie Mitchell
Peter Norvig
Rajat Monga
Wojciech Zaremba
Mathematician