scholarly journals Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision

2019 ◽  
Author(s):  
Courtney J Spoerer ◽  
Tim C Kietzmann ◽  
Johannes Mehrer ◽  
Ian Charest ◽  
Nikolaus Kriegeskorte
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Vision ◽  
Visual Recognition ◽  
Network Models ◽  
Neural Network Models ◽  
Biological Vision ◽  
Visual Systems ◽  
Confidence Threshold ◽  
Recurrent Processing

AbstractDeep feedforward neural network models of vision dominate in both computational neuroscience and engineering. The primate visual system, by contrast, contains abundant recurrent connections. Recurrent signal flow enables recycling of limited computational resources over time, and so might boost the performance of a physically finite brain or model. Here we show: (1) Recurrent convolutional neural network models outperform feedforward convolutional models matched in their number of parameters in large-scale visual recognition tasks on natural images. (2) Setting a confidence threshold, at which recurrent computations terminate and a decision is made, enables flexible trading of speed for accuracy. At a given confidence threshold, the model expends more time and energy on images that are harder to recognise, without requiring additional parameters for deeper computations. (3) The recurrent model’s reaction time for an image predicts the human reaction time for the same image better than several parameter-matched and state-of-the-art feedforward models. (4) Across confidence thresholds, the recurrent model emulates the behaviour of feedforward control models in that it achieves the same accuracy at approximately the same computational cost (mean number of floating-point operations). However, the recurrent model can be run longer (higher confidence threshold) and then outperforms parameter-matched feedforward comparison models. These results suggest that recurrent connectivity, a hallmark of biological visual systems, may be essential for understanding the accuracy, flexibility, and dynamics of human visual recognition.Author summaryDeep neural networks provide the best current models of biological vision and achieve the highest performance in computer vision. Inspired by the primate brain, these models transform the image signals through a sequence of stages, leading to recognition. Unlike brains in which outputs of a given computation are fed back into the same computation, these models do not process signals recurrently. The ability to recycle limited neural resources by processing information recurrently could explain the accuracy and flexibility of biological visual systems, which computer vision systems cannot yet match. Here we report that recurrent processing can improve recognition performance compared to similarly complex feedforward networks. Recurrent processing also enabled models to behave more flexibly and trade off speed for accuracy. Like humans, the recurrent network models can compute longer when an object is hard to recognise, which boosts their accuracy. The model’s recognition times predicted human recognition times for the same images. The performance and flexibility of recurrent neural network models illustrates that modeling biological vision can help us improve computer vision.

scholarly journals APPLICATION OF COMPUTER VISION TECHNOLOGIES FOR THE DEVELOPMENT OF A MODEL FOR THE RECOGNITION OF LESIONS OF CULTIVATED PLANTS

2021 ◽  
Vol 21 (3) ◽  
pp. 5-13
Author(s):  
N.A. Yanishevskaya ◽  
◽  
I.P. Bolodurina ◽  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Computer Vision ◽  
Network Models ◽  
Cultivated Plants ◽  
Industrial Complex ◽  
Neural Network Models ◽  
Crop Disease ◽  
The Russian Federation

In the Russian Federation, the agro-industrial complex is one of the leading sectors of the eco-nomy with a volume of domestic product of 4.5%. Russia owns 10 % of all arable land in the world. According to the data on the sown areas by crops in 2020, most of the agricultural area of Russia is occupied by wheat. The Russian Federation ranks third in the ranking of leading countries in the production of this type of grain crops, as well as leading positions in its export. Brown (leaf) and linear (stem) rust is the most harmful disease of grain crops. It is the reason for the sparseness of wheat crops and leads to a sharp decrease in yield. Therefore, one of the main tasks of farmers is to preserve the crop from diseases. The application of such areas of artificial intelligence as computer vision, machine learning and deep learning is able to cope with this task. These artificial intelligence technologies allow us to successfully solve applied problems of the agro-industrial complex using automated analysis of photographic materials. Aim. To consider the application of computer vision methods for the problem of classification of lesions of cultivated plants on the example of wheat. Materials and methods. The CGIAR Computer Vision for Crop Disease dataset for the crop disease recognition task is taken from the open source Kaggle. It is proposed to use an approach to the re-cognition of lesions of cultivated plants using the well-known neural network models ResNet50, DenseNet169, VGG16 and EfficientNet-B0. Neural network models receive images of wheat as in-put. The output of neural networks is the class of plant damage. To overcome the effect of overfit-ting neural networks, various regularization techniques are investigated. Results. The results of the classification quality, estimated by the software using the F1-score metric, which is the average harmonic between the Precision and Recall measures, are presented. Conclusion. As a result of the conducted research, it was found that the DenseNet model showed the best recognition accuracy us-ing a combination of transfer learning technology and DropOut and L2 regulation technologies to overcome the effect of retraining. The use of this approach allowed us to achieve a recognition ac-curacy of 91%.

scholarly journals Opening the black box of neural networks: methods for interpreting neural network models in clinical applications

2018 ◽  
Vol 6 (11) ◽  
pp. 216-216 ◽  
Author(s):  
Zhongheng Zhang ◽  
◽  
Marcus W. Beck ◽  
David A. Winkler ◽  
Bin Huang ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Black Box ◽  
Clinical Applications ◽  
Neural Network Models

scholarly journals Robotic grasp detection using a novel two-stage approach

2021 ◽  
Vol 1 (1) ◽  
pp. 19-29
Author(s):  
Zhe Chu ◽  
Mengkai Hu ◽  
Xiangyu Chen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Particle Swarm Optimizer ◽  
Neural Network Models ◽  
Two Stage ◽  
The Neural Network ◽  
End To End ◽  
Small Change ◽  
Robotic Grasp

Recently, deep learning has been successfully applied to robotic grasp detection. Based on convolutional neural networks (CNNs), there have been lots of end-to-end detection approaches. But end-to-end approaches have strict requirements for the dataset used for training the neural network models and it’s hard to achieve in practical use. Therefore, we proposed a two-stage approach using particle swarm optimizer (PSO) candidate estimator and CNN to detect the most likely grasp. Our approach achieved an accuracy of 92.8% on the Cornell Grasp Dataset, which leaped into the front ranks of the existing approaches and is able to run at real-time speeds. After a small change of the approach, we can predict multiple grasps per object in the meantime so that an object can be grasped in a variety of ways.

scholarly journals Demand Modelling in Telecommunications

10.14311/1121 ◽  
2009 ◽  
Vol 49 (2) ◽  
Author(s):  
M. Chvalina
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Network Models ◽  
Short Term ◽  
Neural Network Models ◽  
Term Forecast ◽  
Artificial Intelligence Methods ◽  
Demand Modelling

This article analyses the existing possibilities for using Standard Statistical Methods and Artificial Intelligence Methods for a short-term forecast and simulation of demand in the field of telecommunications. The most widespread methods are based on Time Series Analysis. Nowadays, approaches based on Artificial Intelligence Methods, including Neural Networks, are booming. Separate approaches will be used in the study of Demand Modelling in Telecommunications, and the results of these models will be compared with actual guaranteed values. Then we will examine the quality of Neural Network models. 

Artificial Polynomial and Trigonometric Higher Order Neural Network Group Models

2013 ◽  
pp. 78-102 ◽  
Author(s):  
Ming Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Continuous Function ◽  
Trigonometric Polynomial ◽  
Network Models ◽  
Higher Order ◽  
Financial Data ◽  
Neural Network Models ◽  
Piecewise Continuous ◽  
Discontinuous Data

Real world financial data is often discontinuous and non-smooth. Accuracy will be a problem, if we attempt to use neural networks to simulate such functions. Neural network group models can perform this function with more accuracy. Both Polynomial Higher Order Neural Network Group (PHONNG) and Trigonometric polynomial Higher Order Neural Network Group (THONNG) models are studied in this chapter. These PHONNG and THONNG models are open box, convergent models capable of approximating any kind of piecewise continuous function to any degree of accuracy. Moreover, they are capable of handling higher frequency, higher order nonlinear, and discontinuous data. Results obtained using Polynomial Higher Order Neural Network Group and Trigonometric polynomial Higher Order Neural Network Group financial simulators are presented, which confirm that PHONNG and THONNG group models converge without difficulty, and are considerably more accurate (0.7542% - 1.0715%) than neural network models such as using Polynomial Higher Order Neural Network (PHONN) and Trigonometric polynomial Higher Order Neural Network (THONN) models.

Artificial Neural Networks

2011 ◽  
pp. 222-243
Author(s):  
Joarder Kamruzzaman ◽  
Ruhul Sarker
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Network Models ◽  
Neural Network Models ◽  
Network Applications ◽  
The Neural Network ◽  
Artificial Neural ◽  
Neural Network Applications

The primary aim of this chapter is to present an overview of the artificial neural network basics and operation, architectures, and the major algorithms used for training the neural network models. As can be seen in subsequent chapters, neural networks have made many useful contributions to solve theoretical and practical problems in finance and manufacturing areas. The secondary aim here is therefore to provide a brief review of artificial neural network applications in finance and manufacturing areas.

Financial Data Prediction by Artificial Sine and Cosine Trigonometric Higher Order Neural Networks

2021 ◽  
pp. 262-301
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Higher Order ◽  
Financial Data ◽  
Data Simulation ◽  
Neural Network Models ◽  
Data Prediction ◽  
Higher Order Neural Networks

This chapter develops two new nonlinear artificial higher order neural network models. They are sine and sine higher order neural networks (SIN-HONN) and cosine and cosine higher order neural networks (COS-HONN). Financial data prediction using SIN-HONN and COS-HONN models are tested. Results show that SIN-HONN and COS-HONN models are good models for some sine feature only or cosine feature only financial data simulation and prediction compared with polynomial higher order neural network (PHONN) and trigonometric higher order neural network (THONN) models.

scholarly journals Multiple Ensemble Neural Network Models with Fuzzy Response Aggregation for Predicting COVID-19 Time Series: The Case of Mexico

Healthcare ◽  
2020 ◽  
Vol 8 (2) ◽  
pp. 181 ◽  
Author(s):  
Patricia Melin ◽  
Julio Cesar Monica ◽  
Daniela Sanchez ◽  
Oscar Castillo
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Fuzzy Logic ◽  
Network Models ◽  
Neural Network Models ◽  
Validation Data ◽  
Data Set ◽  
Ensemble Neural Networks ◽  
Ensemble Neural Network

In this paper, a multiple ensemble neural network model with fuzzy response aggregation for the COVID-19 time series is presented. Ensemble neural networks are composed of a set of modules, which are used to produce several predictions under different conditions. The modules are simple neural networks. Fuzzy logic is then used to aggregate the responses of several predictor modules, in this way, improving the final prediction by combining the outputs of the modules in an intelligent way. Fuzzy logic handles the uncertainty in the process of making a final decision about the prediction. The complete model was tested for the case of predicting the COVID-19 time series in Mexico, at the level of the states and the whole country. The simulation results of the multiple ensemble neural network models with fuzzy response integration show very good predicted values in the validation data set. In fact, the prediction errors of the multiple ensemble neural networks are significantly lower than using traditional monolithic neural networks, in this way showing the advantages of the proposed approach.

scholarly journals Real-Time Guitar Amplifier Emulation with Deep Learning

2020 ◽  
Vol 10 (3) ◽  
pp. 766 ◽  
Author(s):  
Alec Wright ◽  
Eero-Pekka Damskägg ◽  
Lauri Juvela ◽  
Vesa Välimäki
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Real Time ◽  
Reference Signal ◽  
Network Models ◽  
Neural Network Models ◽  
Desktop Computer ◽  
The Neural Network ◽  
Highly Nonlinear ◽  
The Difference

This article investigates the use of deep neural networks for black-box modelling of audio distortion circuits, such as guitar amplifiers and distortion pedals. Both a feedforward network, based on the WaveNet model, and a recurrent neural network model are compared. To determine a suitable hyperparameter configuration for the WaveNet, models of three popular audio distortion pedals were created: the Ibanez Tube Screamer, the Boss DS-1, and the Electro-Harmonix Big Muff Pi. It is also shown that three minutes of audio data is sufficient for training the neural network models. Real-time implementations of the neural networks were used to measure their computational load. To further validate the results, models of two valve amplifiers, the Blackstar HT-5 Metal and the Mesa Boogie 5:50 Plus, were created, and subjective tests were conducted. The listening test results show that the models of the first amplifier could be identified as different from the reference, but the sound quality of the best models was judged to be excellent. In the case of the second guitar amplifier, many listeners were unable to hear the difference between the reference signal and the signals produced with the two largest neural network models. This study demonstrates that the neural network models can convincingly emulate highly nonlinear audio distortion circuits, whilst running in real-time, with some models requiring only a relatively small amount of processing power to run on a modern desktop computer.

Sign in / Sign up

Export Citation Format

Share Document