A multilayer feedforward neural network model for visual motion perception

1992 ◽  
Vol 9 (4) ◽  
pp. 296-304
Author(s):  
Yang Xianyi ◽  
Guo Aike
Keyword(s):  
Neural Network ◽  
Motion Perception ◽  
Network Model ◽  
Neural Network Model ◽  
Visual Motion ◽  
Feedforward Neural Network ◽  
Visual Motion Perception ◽  
Multilayer Feedforward Neural Network

A Neural Network for the Processing of Optic Flow from Ego-Motion in Man and Higher Mammals

1993 ◽  
Vol 5 (3) ◽  
pp. 374-391 ◽  
Author(s):  
Markus Lappe ◽  
Josef P. Rauschecker
Keyword(s):  
Neural Network ◽  
Motion Perception ◽  
Network Model ◽  
Neural Network Model ◽  
Optic Flow ◽  
Cortical Area ◽  
Visual Motion ◽  
Flow Fields ◽  
Subspace Algorithm ◽  
Motion Flow

Interest in the processing of optic flow has increased recently in both the neurophysiological and the psychophysical communities. We have designed a neural network model of the visual motion pathway in higher mammals that detects the direction of heading from optic flow. The model is a neural implementation of the subspace algorithm introduced by Heeger and Jepson (1990). We have tested the network in simulations that are closely related to psychophysical and neurophysiological experiments and show that our results are consistent with recent data from both fields. The network reproduces some key properties of human ego-motion perception. At the same time, it produces neurons that are selective for different components of ego-motion flow fields, such as expansions and rotations. These properties are reminiscent of a subclass of neurons in cortical area MSTd, the triple-component neurons. We propose that the output of such neurons could be used to generate a computational map of heading directions in or beyond MST.

scholarly journals Exploring and explaining properties of motion processing in biological brains using a neural network

2020 ◽  
Author(s):  
Reuben Rideaux ◽  
Andrew E Welchman
Keyword(s):  
Neural Network ◽  
Motion Perception ◽  
Visual Motion ◽  
Temporal Frequency ◽  
Biological Systems ◽  
Receptive Fields ◽  
Biological Response ◽  
High Spatial Frequency ◽  
Motion Processing ◽  
Visual Motion Perception

ABSTRACTVisual motion perception underpins behaviours ranging from navigation to depth perception and grasping. Our limited access to biological systems constrain our understanding of how motion is processed within the brain. Here we explore properties of motion perception in biological systems by training a neural network (‘MotionNetxy’) to estimate the velocity image sequences. The network recapitulates key characteristics of motion processing in biological brains, and we use our complete access to its structure explore and understand motion (mis)perception at the computational-, neural-, and perceptual-levels. First, we find that the network recapitulates the biological response to reverse-phi motion in terms of direction. We further find that it overestimates the speed of slow reverse-phi motion while underestimating the speed of fast reverse-phi motion because of the correlation between reverse-phi motion and the spatiotemporal receptive fields tuned to motion in opposite directions. Second, we find that the distribution of spatiotemporal tuning properties in the V1 and MT layers of the network are similar to those observed in biological systems. We then show that compared to MT units tuned to fast speeds, those tuned to slow speeds primarily receive input from V1 units tuned to high spatial frequency and low temporal frequency. Third, we find that there is a positive correlation between the pattern-motion and speed selectivity of MT units. Finally, we show that the network captures human underestimation of low coherence motion stimuli, and that this is due to pooling of noise and signal motion. These findings provide biologically plausible explanations for well-known phenomena, and produce concrete predictions for future psychophysical and neurophysiological experiments.

Predicting Stock Market Price Using Neural Network Model

2018 ◽  
Vol 9 (3) ◽  
pp. 84-94 ◽  
Author(s):  
Naliniprava Tripathy
Keyword(s):  
Neural Network ◽  
Stock Market ◽  
Network Model ◽  
Neural Network Model ◽  
Market Price ◽  
Efficient Market Hypothesis ◽  
Feedforward Neural Network ◽  
Neural Network Models ◽  
Daily Movement ◽  
Indian Stock Market

The present article predicts the movement of daily Indian stock market (S&P CNX Nifty) price by using Feedforward Neural Network Model over a period of eight years from January 1st 2008 to April 8th 2016. The prediction accuracy of the model is accessed by normalized mean square error (NMSE) and sign correctness percentage (SCP) measure. The study indicates that the predicted output is very close to actual data since the normalized error of one-day lag is 0.02. The analysis further shows that 60 percent accuracy found in the prediction of the direction of daily movement of Indian stock market price after the financial crises period 2008. The study indicates that the predictive power of the feedforward neural network models reasonably influenced by one-day lag stock market price. Hence, the validity of an efficient market hypothesis does not hold in practice in the Indian stock market. This article is quite useful to the investors, professional traders and regulators for understanding the effectiveness of Indian stock market to take appropriate investment decision in the stock market.

On the Mechanisms Underlying Directional Selectivity

1991 ◽  
Vol 3 (3) ◽  
pp. 333-349 ◽  
Author(s):  
H. Öğmen
Keyword(s):  
Neural Network ◽  
Motion Perception ◽  
Network Model ◽  
Neural Network Model ◽  
Motion Detection ◽  
Data Interpretation ◽  
Directional Selectivity ◽  
Electrophysiological Studies ◽  
Interpretation Problem

Recent efforts in the understanding of motion detection and directional selectivity include electrophysiological studies using single photoreceptor stimulations and a combination of electrophysiology and neuropharmacology. Results of the former have been interpreted in favor of facilitator motion detection models while results of the latter have been interpreted in favor of inhibitory models. In this paper, this conflicting data interpretation problem is addressed by mathematically modeling some effects of neuropharmacological substances and by applying this formalism to a neural network model of directionally selective motion perception. The study offers a possible resolution to the paradox.

scholarly journals A Deep Feedforward Neural Network Model for Image Prediction

2021 ◽  
Vol 1878 (1) ◽  
pp. 012062
Author(s):  
C.C. Lee ◽  
M.H.F Rahiman ◽  
R. A. Rahim ◽  
F. S. A. Saad
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Feedforward Neural Network ◽  
Image Prediction
Sign in / Sign up

Export Citation Format

Share Document