scholarly journals Intrinsic motivation and episodic memories for robot exploration of high-dimensional sensory spaces

2020 ◽  
pp. 105971232092291
Author(s):  
Guido Schillaci ◽  
Antonio Pico Villalpando ◽  
Verena V Hafner ◽  
Peter Hanappe ◽  
David Colliaux ◽  
...  
Keyword(s):  
Neural Networks ◽  
Episodic Memory ◽  
Intrinsic Motivation ◽  
Computational Models ◽  
Deep Neural Networks ◽  
Image Sensor ◽  
Forward Kinematics ◽  
High Dimensional ◽  
Episodic Memories ◽  
Low Dimensional

This work presents an architecture that generates curiosity-driven goal-directed exploration behaviours for an image sensor of a microfarming robot. A combination of deep neural networks for offline unsupervised learning of low-dimensional features from images and of online learning of shallow neural networks representing the inverse and forward kinematics of the system have been used. The artificial curiosity system assigns interest values to a set of pre-defined goals and drives the exploration towards those that are expected to maximise the learning progress. We propose the integration of an episodic memory in intrinsic motivation systems to face catastrophic forgetting issues, typically experienced when performing online updates of artificial neural networks. Our results show that adopting an episodic memory system not only prevents the computational models from quickly forgetting knowledge that has been previously acquired but also provides new avenues for modulating the balance between plasticity and stability of the models.

Forward Kinematic Modeling of Conical-Shaped Continuum Manipulators

Robotica ◽  
2021 ◽  
pp. 1-19
Author(s):  
A. H. Bouyom Boutchouang ◽  
Achille Melingui ◽  
J. J. B. Mvogo Ahanda ◽  
Othman Lakhal ◽  
Frederic Biya Motto ◽  
...  
Keyword(s):  
Neural Networks ◽  
Data Collection ◽  
Robot Control ◽  
Deep Neural Networks ◽  
Forward Kinematics ◽  
Kinematic Modeling ◽  
Experimental Platform ◽  
Continuum Manipulators ◽  
Forward Kinematic

SUMMARY Forward kinematics is essential in robot control. Its resolution remains a challenge for continuum manipulators because of their inherent flexibility. Learning-based approaches allow obtaining accurate models. However, they suffer from the explosion of the learning database that wears down the manipulator during data collection. This paper proposes an approach that combines the model and learning-based approaches. The learning database is derived from analytical equations to prevent the robot from operating for long periods. The database obtained is handled using Deep Neural Networks (DNNs). The Compact Bionic Handling robot serves as an experimental platform. The comparison with existing approaches gives satisfaction.

scholarly journals Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs

2021 ◽  
Vol 47 (1) ◽  
Author(s):  
Fabian Laakmann ◽  
Philipp Petersen
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Initial Conditions ◽  
Activation Function ◽  
Transport Equations ◽  
High Dimensional ◽  
Linear Transport ◽  
Approximation Rates ◽  
Curse Of Dimension ◽  
Efficient Approximation

AbstractWe demonstrate that deep neural networks with the ReLU activation function can efficiently approximate the solutions of various types of parametric linear transport equations. For non-smooth initial conditions, the solutions of these PDEs are high-dimensional and non-smooth. Therefore, approximation of these functions suffers from a curse of dimension. We demonstrate that through their inherent compositionality deep neural networks can resolve the characteristic flow underlying the transport equations and thereby allow approximation rates independent of the parameter dimension.

Deep Convolutional Neural Network for Object Classification

2021 ◽  
pp. 317-343
Author(s):  
Amira Ahmad Al-Sharkawy ◽  
Gehan A. Bahgat ◽  
Elsayed E. Hemayed ◽  
Samia Abdel-Razik Mashali
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Computational Models ◽  
Human Performance ◽  
Deep Neural Networks ◽  
Object Classification ◽  
Classification Problem ◽  
Deep Convolutional Neural Network ◽  
Object Appearance

Object classification problem is essential in many applications nowadays. Human can easily classify objects in unconstrained environments easily. Classical classification techniques were far away from human performance. Thus, researchers try to mimic the human visual system till they reached the deep neural networks. This chapter gives a review and analysis in the field of the deep convolutional neural network usage in object classification under constrained and unconstrained environment. The chapter gives a brief review on the classical techniques of object classification and the development of bio-inspired computational models from neuroscience till the creation of deep neural networks. A review is given on the constrained environment issues: the hardware computing resources and memory, the object appearance and background, and the training and processing time. Datasets that are used to test the performance are analyzed according to the images environmental conditions, besides the dataset biasing is discussed.

scholarly journals Convergence Behavior of DNNs with Mutual-Information-Based Regularization

Entropy ◽  
2020 ◽  
Vol 22 (7) ◽  
pp. 727 ◽  
Author(s):  
Hlynur Jónsson ◽  
Giovanni Cherubini ◽  
Evangelos Eleftheriou
Keyword(s):  
Neural Networks ◽  
Mutual Information ◽  
Low Complexity ◽  
High Dimensional ◽  
Test Accuracy ◽  
Compression Phase ◽  
Hidden Layer ◽  
Low Dimensional ◽  
Fully Connected ◽  
Fully Connected Networks

Information theory concepts are leveraged with the goal of better understanding and improving Deep Neural Networks (DNNs). The information plane of neural networks describes the behavior during training of the mutual information at various depths between input/output and hidden-layer variables. Previous analysis revealed that most of the training epochs are spent on compressing the input, in some networks where finiteness of the mutual information can be established. However, the estimation of mutual information is nontrivial for high-dimensional continuous random variables. Therefore, the computation of the mutual information for DNNs and its visualization on the information plane mostly focused on low-complexity fully connected networks. In fact, even the existence of the compression phase in complex DNNs has been questioned and viewed as an open problem. In this paper, we present the convergence of mutual information on the information plane for a high-dimensional VGG-16 Convolutional Neural Network (CNN) by resorting to Mutual Information Neural Estimation (MINE), thus confirming and extending the results obtained with low-dimensional fully connected networks. Furthermore, we demonstrate the benefits of regularizing a network, especially for a large number of training epochs, by adopting mutual information estimates as additional terms in the loss function characteristic of the network. Experimental results show that the regularization stabilizes the test accuracy and significantly reduces its variance.

scholarly journals Identification of Road-Surface Type Using Deep Neural Networks for Friction Coefficient Estimation

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 612 ◽  
Author(s):  
Eldar Šabanovič ◽  
Vidas Žuraulis ◽  
Olegas Prentkovskis ◽  
Viktor Skrickij
Keyword(s):  
Neural Networks ◽  
Friction Coefficient ◽  
Deep Neural Networks ◽  
Image Sensor ◽  
Video Data ◽  
Road Surface ◽  
Driver Assistance Systems ◽  
Surface Type ◽  
Braking Performance ◽  
The Road

Nowadays, vehicles have advanced driver-assistance systems which help to improve vehicle safety and save the lives of drivers, passengers and pedestrians. Identification of the road-surface type and condition in real time using a video image sensor, can increase the effectiveness of such systems significantly, especially when adapting it for braking and stability-related solutions. This paper contributes to the development of the new efficient engineering solution aimed at improving vehicle dynamics control via the anti-lock braking system (ABS) by estimating friction coefficient using video data. The experimental research on three different road surface types in dry and wet conditions has been carried out and braking performance was established with a car mathematical model (MM). Testing of a deep neural networks (DNN)-based road-surface and conditions classification algorithm revealed that this is the most promising approach for this task. The research has shown that the proposed solution increases the performance of ABS with a rule-based control strategy.

SYNCHRONOUS CHAOS IN HIGH-DIMENSIONAL MODULAR NEURAL NETWORKS

1996 ◽  
Vol 06 (11) ◽  
pp. 2055-2067 ◽  
Author(s):  
THOMAS WENNEKERS ◽  
FRANK PASEMANN
Keyword(s):  
Neural Networks ◽  
Single Unit ◽  
System Size ◽  
Single Units ◽  
High Dimensional ◽  
Coexisting Attractors ◽  
Modular Neural Networks ◽  
Coupled Maps ◽  
Low Dimensional ◽  
The Relationship

The relationship between certain types of high-dimensional neural networks and low-dimensional prototypical equations (neuromodules) is investigated. The high-dimensional systems consist of finitely many pools containing identical, dissipative and nonlinear single-units operating in discrete time. Under the assumption of random connections inside and between pools, the system can be reduced to a set of only a few equations, which — asymptotically in time and system size — describe the behavior of every single unit arbitrarily well. This result can be viewed as synchronization of the single units in each pool. It is stated as a theorem on systems of nonlinear coupled maps, which gives explicit conditions on the single unit dynamics and the nature of the random connections. As an application we compare a 2-pool network with the corresponding two-dimensional dynamics. The bifurcation diagrams of both systems become very similar even for moderate system size (N=50) and large disorder in the connection strengths (50% of mean), despite the fact, that the systems exhibit fairly complex behavior (quasiperiodicity, chaos, coexisting attractors).

scholarly journals Deep Neural Networks for High Dimension, Low Sample Size Data

2017 ◽  
Author(s):  
Bo Liu ◽  
Ying Wei ◽  
Yu Zhang ◽  
Qiang Yang
Keyword(s):  
Neural Networks ◽  
Sample Size ◽  
High Dimension ◽  
Deep Neural Networks ◽  
Genetic Data ◽  
High Dimensional ◽  
Large Sample Size ◽  
Prediction Problem ◽  
The Stability ◽  
Size Data

Deep neural networks (DNN) have achieved breakthroughs in applications with large sample size. However, when facing high dimension, low sample size (HDLSS) data, such as the phenotype prediction problem using genetic data in bioinformatics, DNN suffers from overfitting and high-variance gradients. In this paper, we propose a DNN model tailored for the HDLSS data, named Deep Neural Pursuit (DNP). DNP selects a subset of high dimensional features for the alleviation of overfitting and takes the average over multiple dropouts to calculate gradients with low variance. As the first DNN method applied on the HDLSS data, DNP enjoys the advantages of the high nonlinearity, the robustness to high dimensionality, the capability of learning from a small number of samples, the stability in feature selection, and the end-to-end training. We demonstrate these advantages of DNP via empirical results on both synthetic and real-world biological datasets.

Sign in / Sign up

Export Citation Format

Share Document