Kaiwen Sheng
YOU?
Author Swipe
View article: A neural coding method based on feature sensing
A neural coding method based on feature sensing Open
The novel network contains many sensors, which greatly heightens data transmission burdens. Some networks require the data perceived by sensors for a period to make decisions. Drawing inspiration from the human neural conduction mechanism,…
View article: Effective neural coding method based on maximum entropy
Effective neural coding method based on maximum entropy Open
There are a large number of perceptrons in the new bionic network. To improve the efficiency of data transmission in the bionic network, a maximum entropy neural coding method is proposed. By drawing on the characteristics of human nerve c…
View article: Brain-like learning with exponentiated gradients
Brain-like learning with exponentiated gradients Open
Computational neuroscience relies on gradient descent (GD) for training artificial neural network (ANN) models of the brain. The advantage of GD is that it is effective at learning difficult tasks. However, it produces ANNs that are a poor…
View article: System-level time computation and representation in the suprachiasmatic nucleus revealed by large-scale calcium imaging and machine learning
System-level time computation and representation in the suprachiasmatic nucleus revealed by large-scale calcium imaging and machine learning Open
The suprachiasmatic nucleus (SCN) is the mammalian central circadian pacemaker with heterogeneous neurons acting in concert while each neuron harbors a self-sustained molecular clockwork. Nevertheless, how system-level SCN signals encode t…
View article: Domain-adaptive matching bridges synthetic and <i>in vivo</i> neural dynamics for neural circuit connectivity inference
Domain-adaptive matching bridges synthetic and <i>in vivo</i> neural dynamics for neural circuit connectivity inference Open
Accurately inferring neural circuit connectivity from in vivo recordings is essential for understanding the computations that support behavior and cognition. However, current deep learning approaches are limited by incomplete observability…
View article: U-RISC: An Annotated Ultra-High-Resolution Electron Microscopy Dataset Challenging the Existing Deep Learning Algorithms
U-RISC: An Annotated Ultra-High-Resolution Electron Microscopy Dataset Challenging the Existing Deep Learning Algorithms Open
Connectomics is a developing field aiming at reconstructing the connection of the neural system at the nanometer scale. Computer vision technology, especially deep learning methods used in image processing, has promoted connectomic data an…
View article: Siamese Network-Based All-Purpose-Tracker, a Model-Free Deep Learning Tool for Animal Behavioral Tracking
Siamese Network-Based All-Purpose-Tracker, a Model-Free Deep Learning Tool for Animal Behavioral Tracking Open
Accurate tracking is the basis of behavioral analysis, an important research method in neuroscience and many other fields. However, the currently available tracking methods have limitations. Traditional computer vision methods have problem…
View article: A General LSTM-based Deep Learning Method for Estimating Neuronal Models and Inferring Neural Circuitry
A General LSTM-based Deep Learning Method for Estimating Neuronal Models and Inferring Neural Circuitry Open
Computational neural models are essential tools for neuroscientists to study the functional roles of single neurons or neural circuits. With the recent advances in experimental techniques, there is a growing demand to build up neural model…
View article: Human Perception-based Evaluation Criterion for Ultra-high Resolution Cell Membrane Segmentation
Human Perception-based Evaluation Criterion for Ultra-high Resolution Cell Membrane Segmentation Open
Computer vision technology is widely used in biological and medical data analysis and understanding. However, there are still two major bottlenecks in the field of cell membrane segmentation, which seriously hinder further research: lack o…