SPATIO-TEMPORAL COHERENCE RESONANCE AND FIRING SYNCHRONIZATION IN A NEURAL NETWORK: NOISE AND COUPLING EFFECTS

2009 ◽  
Vol 20 (03) ◽  
pp. 469-478 ◽  
Author(s):  
YANHONG ZHENG ◽  
QISHAO LU ◽  
QINGYUN WANG
Keyword(s):  
Neural Network ◽  
Neuronal Network ◽  
Coupling Strength ◽  
Noise Intensity ◽  
Temporal Coherence ◽  
Square Lattice ◽  
Collective Phenomena ◽  
Coherence Resonance ◽  
Critical Relation ◽  
Spatio Temporal

Effects of noise and coupling on the dynamics of a square lattice neuronal network are studied in this paper. Patterns and collective phenomena such as firing synchronization are investigated in networks with dynamics of each neuron described by FitzHugh–Nagumo model. As the noise intensity is increased, typical patterns emerge spatially, which propagate through the networks in the form of circular waves. Further increasing noise can destroy the circular wave, and then some random portraits appear. Moreover, the spatio-temporal coherence and the transitions of firing synchronization characterized by the rate of firing are investigated as the noise intensity and the coupling strength vary. The maximal coherence of the oscillations could be found at two optimal noise intensities (or coupling strength) for appropriate coupling strength (or noise intensity), displaying coherence bi -resonance. Finally, the critical relation between the noise intensity and the coupling strength is given to investigate the occurrence of firing synchronization in the network.

NOISE-INDUCED PATTERN FORMATION AND SYNCHRONIZATION IN A SQUARE-LATTICE NEURONAL NETWORK

2012 ◽  
Vol 22 (05) ◽  
pp. 1250115 ◽  
Author(s):  
YANHONG ZHENG ◽  
QINGYUN WANG ◽  
CHUNBIAO GAN
Keyword(s):  
Neural Network ◽  
Pattern Formation ◽  
Coupling Strength ◽  
Noise Intensity ◽  
Critical Value ◽  
Square Lattice ◽  
Collective Dynamic ◽  
Critical Relation ◽  
Spatially Periodic ◽  
Dynamic Phenomena

Effects of noise on the collective dynamic phenomena such as patterns and firing synchronization are studied in a square-lattice FitzHugh–Nagumo neural network with gap junctions. It is shown that as the noise intensity is above a critical value, typical patterns can emerge and propagate through the network in the form of coexisting circular waves and parallel ones with spatially periodic structure. Circular waves can change from a single-array to double-array as the noise increases. Furthermore, we can observe that spatial evolutions of patterns can exhibit different styles as the noise is changed. In addition, we study noise-induced firing synchronization of neurons. In particular, firing synchronization can be enhanced, and then can reach a saturated value as the noise is large enough. More interestingly, it is found that the stronger the coupling strength is, the larger the noise intensity is needed to make neurons fire. Finally, the critical relation between the noise intensity and the coupling strength is given to investigate the occurrence of firing synchronization in the network.

scholarly journals Machine learning estimation of tissue optical properties

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Brett H. Hokr ◽  
Joel N. Bixler
Keyword(s):  
Neural Network ◽  
Optical Properties ◽  
Biological Tissues ◽  
Homogeneous Layer ◽  
In Vivo Measurement ◽  
Tissue Optical Properties ◽  
The Neural Network ◽  
Spatio Temporal ◽  
Fully Connected

AbstractDynamic, in vivo measurement of the optical properties of biological tissues is still an elusive and critically important problem. Here we develop a technique for inverting a Monte Carlo simulation to extract tissue optical properties from the statistical moments of the spatio-temporal response of the tissue by training a 5-layer fully connected neural network. We demonstrate the accuracy of the method across a very wide parameter space on a single homogeneous layer tissue model and demonstrate that the method is insensitive to parameter selection of the neural network model itself. Finally, we propose an experimental setup capable of measuring the required information in real time in an in vivo environment and demonstrate proof-of-concept level experimental results.

scholarly journals FetNet: a recurrent convolutional network for occlusion identification in fetoscopic videos

2020 ◽  
Vol 15 (5) ◽  
pp. 791-801 ◽  
Author(s):  
Sophia Bano ◽  
Francisco Vasconcelos ◽  
Emmanuel Vander Poorten ◽  
Tom Vercauteren ◽  
Sebastien Ourselin ◽  
...  
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Laser Photocoagulation ◽  
Short Term Memory ◽  
Total Duration ◽  
Frame Rate ◽  
Superior Performance ◽  
Computer Assisted ◽  
Convolutional Network ◽  
Spatio Temporal

Abstract Purpose Fetoscopic laser photocoagulation is a minimally invasive surgery for the treatment of twin-to-twin transfusion syndrome (TTTS). By using a lens/fibre-optic scope, inserted into the amniotic cavity, the abnormal placental vascular anastomoses are identified and ablated to regulate blood flow to both fetuses. Limited field-of-view, occlusions due to fetus presence and low visibility make it difficult to identify all vascular anastomoses. Automatic computer-assisted techniques may provide better understanding of the anatomical structure during surgery for risk-free laser photocoagulation and may facilitate in improving mosaics from fetoscopic videos. Methods We propose FetNet, a combined convolutional neural network (CNN) and long short-term memory (LSTM) recurrent neural network architecture for the spatio-temporal identification of fetoscopic events. We adapt an existing CNN architecture for spatial feature extraction and integrated it with the LSTM network for end-to-end spatio-temporal inference. We introduce differential learning rates during the model training to effectively utilising the pre-trained CNN weights. This may support computer-assisted interventions (CAI) during fetoscopic laser photocoagulation. Results We perform quantitative evaluation of our method using 7 in vivo fetoscopic videos captured from different human TTTS cases. The total duration of these videos was 5551 s (138,780 frames). To test the robustness of the proposed approach, we perform 7-fold cross-validation where each video is treated as a hold-out or test set and training is performed using the remaining videos. Conclusion FetNet achieved superior performance compared to the existing CNN-based methods and provided improved inference because of the spatio-temporal information modelling. Online testing of FetNet, using a Tesla V100-DGXS-32GB GPU, achieved a frame rate of 114 fps. These results show that our method could potentially provide a real-time solution for CAI and automating occlusion and photocoagulation identification during fetoscopic procedures.

Sign in / Sign up

Export Citation Format

Share Document