Yunjiao Wang

Dr. Yunjiao Wang

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 February 2021 in Algorithms
Verified
Journal Article
Open access
PDF file
NKNalinda Kulathunga
Nalinda Kulathunga
NRNishath Rajiv Ranasinghe
Nishath Rajiv Ranasinghe
DVDaniel Vrinceanu
Daniel Vrinceanu
ZKZackary Kinsman
Zackary Kinsman
LHLei Huang
Lei Huang
YWYunjiao Wang
Yunjiao Wang
The nonlinearity of activation functions used in deep learning models is crucial for the success of predictive models. Several simple nonlinear functions, including Rectified Linear Unit (ReLU) and Leaky-ReLU (L-ReLU) are commonly used in neural networks to impose the nonlinearity. In practice, these functions remarkably enhance the model accuracy. However, there is limited insight into the effects of nonlinearity in neural networks on their performance. Here, we investigate the performance of neural network models as a function of nonlinearity using ReLU and L-ReLU activation functions in the context of different model architectures and data domains. We use entropy as a measurement of the randomness, to quantify the effects of nonlinearity in different architecture shapes on the performance of neural networks. We show that the ReLU nonliearity is a better choice for activation function mostly when the network has sufficient number of parameters. However, we found that the image classification models with transfer learning seem to perform well with L-ReLU in fully connected layers. We show that the entropy of hidden layer outputs in neural networks can fairly represent the fluctuations in information loss as a function of nonlinearity. Furthermore, we investigate the entropy profile of shallow neural networks as a way of representing their hidden layer dynamics.

27 April 2020 in Journal of Computational Neuroscience
Verified
Journal Article
Closed access
PDF file
YWYunjiao Wang
Yunjiao Wang
ZKZachary P. Kilpatrick
Zachary P. Kilpatrick
KJKrešimir Josić
Krešimir Josić

10 October 2019 in bioRxiv
Verified
Preprint
Open access
PDF file
YWYunjiao Wang
Yunjiao Wang
ZKZachary P Kilpatrick
Zachary P Kilpatrick
KJKrešimir Josić
Krešimir Josić
Ambiguous visual images can generate dynamic and stochastic switches in perceptual interpretation known as perceptual rivalry. Such dynamics have primarily been studied in the context of rivalry between two percepts, but there is growing interest in the neural mechanisms that drive rivalry between more than two percepts. In recent experiments, we showed that split images presented to each eye lead to subjects perceiving four stochastically alternating percepts (Jacot-Guillarmod et al., 2017): two single eye images and two interocularly grouped images. Here we propose a hierarchical neural network model that exhibits dynamics consistent with our experimental observations. The model consists of two levels, with the first representing monocular activity, and the second representing activity in higher visual areas. The model produces stochastically switching solutions, whose dependence on task parameters is consistent with four generalized Levelt Propositions. Our neuromechanistic model also allowed us to probe the roles of inter-actions between populations at the network levels. Stochastic switching at the lower level representing alternations between single eye percepts dominated, consistent with experiments.

12 November 2024 in The PUMP Journal of Undergraduate Research
Verified
Journal Article
Open access
PDF file
JFJoshua Farley
Joshua Farley
CYCarrie Yang
Carrie Yang
YWYunjiao Wang
Yunjiao Wang
In this work, we consider the areas of the regions enclosed by generalized Koch curves. We derived formulas for several classes of generalized Koch snowflakes. We also obtained a formula that can be used for computing areas of more complex snowflakes.