The curious case of developmental BERTology: On sparsity, transfer learning, generalization and the brain
arXiv:2007.03774
Abstract
In this essay, we explore a point of intersection between deep learning and neuroscience, through the lens of large language models, transfer learning and network compression. Just like perceptual and cognitive neurophysiology has inspired effective deep neural network architectures which in turn make a useful model for understanding the brain, here we explore how biological neural development might inspire efficient and robust optimization procedures which in turn serve as a useful model for the maturation and aging of the brain.
arXiv comment9 pages, 5 figures, 1 table
References in corpus (15)
- Language Models are Few-Shot Learners
- Reconciling modern machine learning practice and the bias-variance trade-off
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
- To prune, or not to prune: exploring the efficacy of pruning for model compression
- The State of Sparsity in Deep Neural Networks
- Deep Learning: A Critical Appraisal
- The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
- A Survey on Neural Architecture Search
- Essentially No Barriers in Neural Network Energy Landscape
- One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
- Proving the Lottery Ticket Hypothesis: Pruning is All You Need
- How Can We Be So Dense? The Benefits of Using Highly Sparse Representations
- Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT
- Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection