Прати
Jonathan Frankle
Jonathan Frankle
Databricks
Верификована је имејл адреса на databricks.com - Почетна страница
Наслов
Навело
Навело
Година
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
J Frankle, M Carbin
International Conference on Learning Representations, 2019
42092019
What is the State of Neural Network Pruning?
D Blalock, JJG Ortiz, J Frankle, J Guttag
Conference on Machine Learning and Systems, 2020
13912020
Linear Mode Connectivity and the Lottery Ticket Hypothesis
J Frankle, GK Dziugaite, DM Roy, M Carbin
International Conference on Machine Learning, 2020
6062020
Comparing Rewinding and Fine-tuning in Neural Network Pruning
A Renda, J Frankle, M Carbin
International Conference on Learning Representations, 2020
4572020
The Lottery Ticket Hypothesis for Pre-Trained BERT Networks
T Chen, J Frankle, S Chang, S Liu, Y Zhang, Z Wang, M Carbin
Neural Information Processing Systems, 2020
4092020
The Perpetual Line-Up: Unregulated Police Face Recognition in America
C Garvie, A Bedoya, J Frankle
Georgetown Law, Center on Privacy & Technology, 2016
4032016
Stabilizing the Lottery Ticket Hypothesis / The Lottery Ticket Hypothesis at Scale
J Frankle, GK Dziugaite, DM Roy, M Carbin
arXiv, 2019
391*2019
Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs
MMLNLP Team
https://www.databricks.com/blog/mpt-7b, 2023
277*2023
Pruning Neural Networks at Initialization: Why are We Missing the Mark?
J Frankle, GK Dziugaite, DM Roy, M Carbin
International Conference on Learning Representations, 2021
2662021
The lottery ticket hypothesis: Training pruned neural networks
J Frankle, M Carbin
arXiv preprint arXiv:1803.03635 2, 2018
2022018
The Early Phase of Neural Network Training
J Frankle, DJ Schwab, AS Morcos
International Conference on Learning Representations, 2020
1912020
Example-Directed Synthesis: A Type-Theoretic Interpretation
J Frankle, PM Osera, D Walker, S Zdancewic
POPL 51 (1), 802-815, 2016
1562016
Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs
J Frankle, DJ Schwab, AS Morcos
International Conference on Learning Representations, 2021
1462021
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
T Chen, J Frankle, S Chang, S Liu, Y Zhang, M Carbin, Z Wang
Conference on Computer Vision and Pattern Recognition, 2021
1412021
Facial-Recognition Software Might Have a Racial Bias Problem
C Garvie, J Frankle
The Atlantic 7, 2016
1362016
Lora learns less and forgets less
D Biderman, J Portes, JJG Ortiz, M Paul, P Greengard, C Jennings, ...
Transactions on Machine Learning Research, 2024
1002024
Practical Accountability of Secret Processes
J Frankle, S Park, D Shaar, S Goldwasser, D Weitzner
27th USENIX Security Symposium (USENIX Security 18), 657-674, 2018
932018
Are all negatives created equal in contrastive instance discrimination?
TT Cai, J Frankle, DJ Schwab, AS Morcos
Science Meets Engineering of Deep Learning Workshop (ICLR), 2021
90*2021
Desirable Inefficiency
P Ohm, J Frankle
Fla. L. Rev. 70, 777, 2018
732018
The shift from models to compound ai systems
M Zaharia, O Khattab, L Chen, JQ Davis, H Miller, C Potts, J Zou, ...
Berkeley Artificial Intelligence Research Lab. Available online at: https …, 2024
682024
Систем тренутно не може да изврши ову радњу. Пробајте поново касније.
Чланци 1–20