Search results for "Artificial intelligence"
showing 10 items of 6122 documents
Why Cortices ? Neural Computation in the Vertebrate Visual System
1989
We propose three high level structural principles of neural networks in the vertebrate visual cortex and discuss some of their computational implications for early vision: a) Lamination, average axonal and dendritic domains, and intrinsic feedback determine the spatio-temporal interactions in cortical processing. Possible applications of the resulting filters include continuous motion perception and the direct measurement of high-level parameters of image flow, b) Retinotopic mapping is an emergent property of massively parallel connections. With a local intrinsic operation in the target area, mapping combines to a space-variant image processing system as would be useful in the analysis of …
Increasing sample efficiency in deep reinforcement learning using generative environment modelling
2020
Road Detection for Reinforcement Learning Based Autonomous Car
2020
Human mistakes in traffic often have terrible consequences. The long-awaited introduction of self-driving vehicles may solve many of the problems with traffic, but much research is still needed before cars are fully autonomous.In this paper, we propose a new Road Detection algorithm using online supervised learning based on a Neural Network architecture. This algorithm is designed to support a Reinforcement Learning algorithm (for example, the standard Proximal Policy Optimization or PPO) by detecting when the car is in an adverse condition. Specifically, the PPO gets a penalty whenever the virtual automobile gets stuck or drives off the road with any of its four wheels.Initial experiments …
Efficient pruning of multilayer perceptrons using a fuzzy sigmoid activation function
2006
This Letter presents a simple and powerful pruning method for multilayer feed forward neural networks based on the fuzzy sigmoid activation function presented in [E. Soria, J. Martin, G. Camps, A. Serrano, J. Calpe, L. Gomez, A low-complexity fuzzy activation function for artificial neural networks, IEEE Trans. Neural Networks 14(6) (2003) 1576-1579]. Successful performance is obtained in standard function approximation and channel equalization problems. Pruning allows to reduce network complexity considerably, achieving a similar performance to that obtained by unpruned networks.
Classical Training Methods
2006
This chapter reviews classical training methods for multilayer neural networks. These methods are widely used for classification and function modelling tasks. Nevertheless, they show a number of flaws or drawbacks that should be addressed in the development of such systems. They work by searching the minimum of an error function which defines the optimal behaviour of the neural network. Different standard problems are used to show the capabilities of these models; in particular, we have benchmarked the algorithms in a nonlinear classification problem and in three function modelling problems.
Deep learning strategies for automatic fault diagnosis in photovoltaic systems by thermographic images
2021
Abstract Losses of electricity production in photovoltaic systems are mainly caused by the presence of faults that affect the efficiency of the systems. The identification of any overheating in a photovoltaic module, through the thermographic non-destructive test, may be essential to maintain the correct functioning of the photovoltaic system quickly and cost-effectively, without interrupting its normal operation. This work proposes a system for the automatic classification of thermographic images using a convolutional neural network, developed via open-source libraries. To reduce image noise, various pre-processing strategies were evaluated, including normalization and homogenization of pi…
Pose classification using support vector machines
2000
In this work a software architecture is presented for the automatic recognition of human arm poses. Our research has been carried on in the robotics framework. A mobile robot that has to find its path to the goal in a partially structured environment can be trained by a human operator to follow particular routes in order to perform its task quickly. The system is able to recognize and classify some different poses of the operator's arms as direction commands like "turn-left", "turn-right", "go-straight", and so on. A binary image of the operator silhouette is obtained from the gray-level input. Next, a slice centered on the silhouette itself is processed in order to compute the eigenvalues …
CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning
2020
Reinforcement Learning (RL) is a general framework concerned with an agent that seeks to maximize rewards in an environment. The learning typically happens through trial and error using explorative methods, such as \(\epsilon \)-greedy. There are two approaches, model-based and model-free reinforcement learning, that show concrete results in several disciplines. Model-based RL learns a model of the environment for learning the policy while model-free approaches are fully explorative and exploitative without considering the underlying environment dynamics. Model-free RL works conceptually well in simulated environments, and empirical evidence suggests that trial and error lead to a near-opti…
On the use of artificial intelligence tools for fracture forecast in cold forming operations
2006
Abstract The design of cold forming processes requires the availability of a procedure able to deal with the prevention of ductile fracture. In fact, the ability to predict fracture represents a powerful tool to improve the production quality in mechanical industry. In this paper, artificial intelligence (AI) techniques are applied to ductile fracture prediction in cold forming operations. The main advantage of the application of AI tools and in particular, of artificial neural networks (ANN), is the possibility to obtain a predictive tool with a wide applicability. The prediction results obtained in this paper fully demonstrate the usefulness of the proposed approach.
Identification of the Parameters of Reduced Vector Preisach Model by Neural Networks
2008
This paper presents a methodology for identifying reduced vector Preisach model parameters by using neural networks. The neural network used is a multiplayer perceptron trained with the Levenberg-Marquadt training algorithm. The network is trained by some hysteresis data, which are generated by using reduced vector Preisach model with preassigned parameters. It is shown how a properly trained network is able to find the parameters needed to best fit a magnetization hysteresis curve.