Search Results for author: Yuhai Tu

Found 14 papers, 2 papers with code

One nose but two nostrils: Learn to align with sparse connections between two olfactory cortices

no code implementations6 May 2024 Bo Liu, Shanshan Qin, Venkatesh Murthy, Yuhai Tu

We next compared the alignment performance of local Hebbian rule and the global stochastic-gradient-descent (SGD) learning for artificial neural networks.

Temperature Compensation through Kinetic Regulation in Biochemical Oscillators

no code implementations25 Jan 2024 Haochen Fu, Chenyi Fei, Qi Ouyang, Yuhai Tu

From a general timescale invariance, we show that TC relies on existence of certain period-lengthening reactions wherein the period of the system increases strongly with the rates in these reactions.

Maximal Domain Independent Representations Improve Transfer Learning

no code implementations1 Jun 2023 Adrian Shuai Li, Elisa Bertino, Xuan-Hong Dang, Ankush Singla, Yuhai Tu, Mark N Wegman

To address this shortcoming, we developed a new algorithm wherein a stronger constraint is imposed to minimize the DDRep by using a KL divergent loss for the DDRep in order to create the maximal DIRep that enhances transfer learning performance.

Domain Adaptation Transfer Learning

Effective Dynamics of Generative Adversarial Networks

no code implementations8 Dec 2022 Steven Durr, Youssef Mroueh, Yuhai Tu, Shenshen Wang

Generative adversarial networks (GANs) are a class of machine-learning models that use adversarial training to generate new samples with the same (potentially very complex) statistics as the training samples.

Diversity valid

Stochastic gradient descent introduces an effective landscape-dependent regularization favoring flat solutions

no code implementations2 Jun 2022 Ning Yang, Chao Tang, Yuhai Tu

Empirical studies showed a strong correlation between flatness of the loss landscape at a solution and its generalizability, and stochastic gradient descent (SGD) is crucial in finding the flat solutions.

The activity-weight duality in feed forward neural networks: The geometric determinants of generalization

1 code implementation21 Mar 2022 Yu Feng, Yuhai Tu

The contribution from a given eigen-direction is the product of two geometric factors (determinants): the sharpness of the loss landscape and the standard deviation of the dual weights, which is found to scale with the weight norm of the solution.

Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent

no code implementations2 Dec 2021 Wei zhang, Mingrui Liu, Yu Feng, Xiaodong Cui, Brian Kingsbury, Yuhai Tu

We conduct extensive studies over 18 state-of-the-art DL models/tasks and demonstrate that DPSGD often converges in cases where SSGD diverges for large learning rates in the large batch setting.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Phases of learning dynamics in artificial neural networks: with or without mislabeled data

no code implementations16 Jan 2021 Yu Feng, Yuhai Tu

Without mislabeled data, we find that the SGD learning dynamics transitions from a fast learning phase to a slow exploration phase, which is associated with large changes in order parameters that characterize the alignment of SGD gradients and their mean amplitude.

Why Does Decentralized Training Outperform Synchronous Training In The Large Batch Setting?

no code implementations1 Jan 2021 Wei zhang, Mingrui Liu, Yu Feng, Brian Kingsbury, Yuhai Tu

We conduct extensive studies over 12 state-of-the-art DL models/tasks and demonstrate that DPSGD consistently outperforms SSGD in the large batch setting; and DPSGD converges in cases where SSGD diverges for large learning rates.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

How neural networks find generalizable solutions: Self-tuned annealing in deep learning

no code implementations6 Jan 2020 Yu Feng, Yuhai Tu

Despite the tremendous success of Stochastic Gradient Descent (SGD) algorithm in deep learning, little is known about how SGD finds generalizable solutions in the high-dimensional weight space.


Error-speed correlations in biopolymer synthesis

no code implementations30 May 2019 Davide Chiuchiú, Yuhai Tu, Simone Pigolotti

In this paper, we study fluctuations of error and speed in biopolymer synthesis and show that they are in general correlated.

Continual Learning with Self-Organizing Maps

no code implementations19 Apr 2019 Pouya Bashivan, Martin Schrimpf, Robert Ajemian, Irina Rish, Matthew Riemer, Yuhai Tu

Most previous approaches to this problem rely on memory replay buffers which store samples from previously learned tasks, and use them to regularize the learning on new ones.

Continual Learning

Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference

2 code implementations ICLR 2019 Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, Gerald Tesauro

In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples.

Continual Learning Meta-Learning

Deciphering gene regulation from gene expression dynamics using deep neural network

no code implementations23 Jul 2018 Jingxiang Shen, Mariela D. Petkova, Yuhai Tu, Feng Liu, Chao Tang

Furthermore, the regulation network it uncovers is strikingly similar to the one inferred from experiments.

Cannot find the paper you are looking for? You can Submit a new open access paper.