AI & machine learning2018 · shared on Hacker News

The Lottery Ticket Hypothesis: Finding Small, Trainable Neural Networks

Explore The Lottery Ticket Hypothesis: Finding Small, Trainable Neural Networks, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.

The conversation around the idea.

Links found in the discussion

S1: A $6 R1 competitor?

Ask HN: What projects are you working on now?

OpenAI says it has evidence DeepSeek used its model to train competitor

Ask HN: What's the best paper you've read in 2020?

Mammals dream about the world they are about to experience before they are born

Computer scientists prove why bigger neural networks do better

Zamba2-7B

Researchers propose faster, more efficient alternatives to backpropagation

Statistical Process Control in Python

Researchers unveil a pruning algorithm to shrink deep learning models

Smarter Training of Neural Networks

Exploring Weight Agnostic Neural Networks

Proving the Lottery Ticket Hypothesis: Pruning is All You Need

Learning@home hivemind – train large neural networks across the internet

Deep Learning's Diminishing Returns

The Lottery Ticket Hypothesis: Finding Small, Trainable Neural Networks

The lottery ticket hypothesis: why neural networks work

Neural nets typically contain smaller “subnetworks” that can often learn faster

Neurons that fire together, wire together, but how?

An overview of the theory of overparameterized machine learning

Notes on Weight Initialization for Deep Neural Networks

The AI Research SuperCluster

No Brainer (2015)

Weight-sparse transformers have interpretable circuits [pdf]

Substitute certain overhyped programming terms with more accurate replacements

SparseGPT: Language Models Can Be Accurately Pruned in One-Shot

See the First Complete Map of an Insect’s Brain

It’s infuriatingly hard to understand how closed models train on their input

AI intensifies fight against ‘paper mills’ that churn out fake research

The Lottery Ticket Hypothesis: Training Pruned Neural Networks

I won an ML lottery ticket, then squandered it

Can Generalist Foundation Models Beat Special-Purpose Tuning?Medicine Case Study

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (2019)

The Transformer Family

I won an ML lottery ticket, then squandered it

The Lottery Ticket Hypothesis: finding sparse trainable NNs with 90% less params

Show HN: SparseLab–real sparse training(CSR+custom kernel) in PyTorch, CPU-first

One idea leads to another.