STUDYING THE IMPACT OF LANGUAGE ON THE MIND BY CONSTRUCTING ROBOTS THAT HAVE LANGUAGE

2012 ◽  
Vol 15 (03n04) ◽  
pp. 1250051
Author(s):  
DOMENICO PARISI
Keyword(s):  
Neural Network ◽  
Neural Model ◽  
Position Paper ◽  
Human Beings ◽  
Behavioral Repertoire ◽  
Modular Model ◽  
The Neural Network ◽  
The Mind ◽  
The Impact

In this position paper we discuss how language influences the mind by comparing robots that have language with robots that do not have language. Robots with language respond more adaptively to objects belonging to different categories and requiring different behaviors compared to robots without language, and it is possible to show that categories of objects are represented differently in the neural network which controls the behavior of the two types of robots. By exposing the robots to sounds which co-vary systematically with specific aspects of their experience, the robots can distinguish nouns from verbs and can respond appropriately to simple noun–verb sentences. Robots can also be used to show that, while all animals develop a mental (neural) model of their environment which incorporates the co-variations among different aspects of their experiences, human beings develop a more analytical and modular model because specific sounds co-vary with different aspects of their experiences — and this may explain why human beings have a more articulated and creative behavioral repertoire.

scholarly journals Towards Enhanced Performance of Neural-Network-Based Fault Detection Using an Sequential D-Optimum Experimental Design

2018 ◽  
Vol 8 (8) ◽  
pp. 1290 ◽  
Author(s):  
Beata Mrugalska
Keyword(s):  
Neural Network ◽  
Experimental Design ◽  
Fault Detection ◽  
Network Models ◽  
Neural Model ◽  
Neural Network Models ◽  
Optimum Experimental Design ◽  
The Neural Network ◽  
Adaptive Thresholds ◽  
Linear Neural Network

Increasing expectations of industrial system reliability require development of more effective and robust fault diagnosis methods. The paper presents a framework for quality improvement on the neural model applied for fault detection purposes. In particular, the proposed approach starts with an adaptation of the modified quasi-outer-bounding algorithm towards non-linear neural network models. Subsequently, its convergence is proven using quadratic boundedness paradigm. The obtained algorithm is then equipped with the sequential D-optimum experimental design mechanism allowing gradual reduction of the neural model uncertainty. Finally, an emerging robust fault detection framework on the basis of the neural network uncertainty description as the adaptive thresholds is proposed.

Combined Trajectory Planning and Tracking for Autonomous Vehicles on Deformable Terrains

2020 ◽  
Author(s):  
James Dallas ◽  
Yifan Weng ◽  
Tulga Ersal
Keyword(s):  
Neural Network ◽  
Trajectory Planning ◽  
Autonomous Vehicles ◽  
Performance Metrics ◽  
Soft Soil ◽  
Computation Time ◽  
Operating Conditions ◽  
The Neural Network ◽  
Vehicle Response ◽  
The Impact

Abstract In this work, a novel combined trajectory planner and tracking controller is developed for autonomous vehicles operating on off-road deformable terrains. Common approaches to trajectory planning and tracking often rely on model-dependent schemes, which utilize a simplified model to predict the impact of control inputs to future vehicle response. However, in an off-road context and especially on deformable terrains, accurately modeling the vehicle response for predictive purposes can be challenging due to the complexity of the tire-terrain interaction and limitations of state-of-the-art terramechanics models in terms of operating conditions, computation time, and continuous differentiability. To address this challenge and improve vehicle safety and performance through more accurate prediction of the plant response, in this paper, a nonlinear model predictive control framework is presented that accounts for terrain deformability explicitly using a neural network terramechanics model for deformable terrains. The utility of the proposed scheme is demonstrated on high fidelity simulations for a notional lightweight military vehicle on soft soil. It is shown that the neural network based controller can outperform a baseline Pacejka model based scheme by improving on performance metrics associated with the cost function. In more severe maneuvers, the neural network based controller can achieve sufficient fidelity as compared to the plant to complete maneuvers that lead to failure for the Pacejka based controller. Finally, it is demonstrated that the proposed framework is conducive to real-time implementability.

Motor Schema Model Learned by Structural Neural Networks

1990 ◽  
Vol 2 (4) ◽  
pp. 258-265
Author(s):  
Toshio Tsuji ◽  
◽  
Yusuke Ishida ◽  
Koji Ito ◽  
Mitsuo Nagamachi ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Human Beings ◽  
Motion System ◽  
The Neural Network ◽  
Action Sequences ◽  
Schema Model ◽  
Part Model

Human beings remember plans concerning typical motions which occur frequently as schema, and by selecting suitable schema depending on conditions, generate muscular motion almost unconsciously. Though a motor schema represents typical motions, it is equipped with superior plan structure taking into consideration the concurrency and seriality of motions as seen in grasping actions and walking motions, and the structure of plans can be acquired by learning. In this paper, a study is made of the modeling of such motor schema with the use of neural networks. For this purpose, the neural network is structured beforehand into the part which generates action sequences in the form containing concurrency (concurrent action generation part) and the part which modifies the action sequences to satisfy constraints which cannot be executed concurrently (constraint representation part). After learning in each part model the neural network can generate motion sequences while taking into consideration the seriality and concurrency of motion by combining the parts at the time of execution. Finally, this model is applied to the formation of typewriting action motor schema, and it is demonsted that generates motion sequences which take into consideration the constraint of the motion system accompanying the execution of motion.

scholarly journals Development of an algorithm for object access system automation based on face recognition using a neural network

Connectivity ◽  
2020 ◽  
Vol 145 (3) ◽  
Author(s):  
V. S. Orlenko ◽  
◽  
I. I. Kolosinsʹkyy
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Neural Model ◽  
Large Datasets ◽  
Second Step ◽  
Test Set ◽  
Access System ◽  
The Neural Network ◽  
The Face ◽  
Face Search

The article deals with the technical side of face recognition — the neural network. The advantages of the neural network for identification of the person are substantiated, the stages of comparison of two images are considered. The first step is defined as the face search in the photo. Using several tests, the best neural network was identified, which allowed to effectively obtain a normalized image of a person’s face. The second step is to find the features of the person, for which the comparative analysis is performed. It was this stage that became the main point in this article — 16 sets of tests were carried out, each test set has 12 tests inside. Two large datasets were used for the study to evaluate the effectiveness of the algorithms not only in ideal circumstances but also in the field. The results of the study allowed us to determine the best method and neural model for finding a face and dividing it into parts. It is determined which part of the face the algorithm recognizes best — it will allow making adjustments to the location of the camera.

scholarly journals Language switching training modulates the neural network of non-linguistic cognitive control

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0247100
Author(s):  
Mo Chen ◽  
Fengyang Ma ◽  
Zhaoqi Zhang ◽  
Shuhua Li ◽  
Man Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Cognitive Control ◽  
Structural Equation ◽  
Structural Equation Models ◽  
Brain Regions ◽  
Anterior Cingulate ◽  
Language Switching ◽  
Dorsal Anterior Cingulate Cortex ◽  
The Neural Network ◽  
The Impact

Bilingual language experience, such as switching between languages, has been shown to shape both cognitive and neural mechanisms of non-linguistic cognitive control. However, the neural adaptations induced by language switching remain unclear. Using fMRI, the current study examined the impact of short-term language switching training on the neural network of domain-general cognitive control for unbalanced Chinese-English bilinguals. Effective connectivity maps were constructed by using the extended unified structural equation models (euSEM) within 10 common brain regions involved in both language control and domain-general cognitive control. Results showed that, the dorsal anterior cingulate cortex/pre-supplementary motor area (dACC/pre-SMA) lost connection from the right thalamus after training, suggesting that less neural connectivity was required to complete the same domain-general cognitive control task. These findings not only provide direct evidence for the modulation of language switching training on the neural interaction of domain-general cognitive control, but also have important implications for revealing the potential neurocognitive adaptation effects of specific bilingual language experiences.

scholarly journals Evaluation of VIIRS Neural Network Cloud Detection against Current Operational Cloud Masks

2020 ◽  
Author(s):  
Charles H. White ◽  
Andrew K. Heidinger ◽  
Steven A. Ackerman
Keyword(s):  
Neural Network ◽  
Optical Depth ◽  
Infrared Imaging ◽  
Regional Analysis ◽  
True Positive Rate ◽  
Orthogonal Polarization ◽  
Cloud Detection ◽  
The Neural Network ◽  
Cloud Mask ◽  
The Impact

Abstract. Cloud properties are critical to our understanding of weather and climate variability, but their estimation from satellite imagers is a nontrivial task. In this work, we aim to improve cloud detection which is the most fundamental cloud property. We use a neural network applied to Visible Infrared Imaging Radiometer Suite (VIIRS) measurements to determine whether an imager pixel is cloudy or cloud-free. The neural network is trained and evaluated using four years (2016–2019) of coincident measurements between VIIRS and the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP). We successfully address the lack of sun glint in the collocation dataset with a simple semi-supervised learning approach. The results of the neural network are then compared with two operational cloud masks: the MODIS-VIIRS Continuity Cloud Mask (MVCM) and the NOAA Enterprise Cloud Mask (ECM). We find that the neural network outperforms both operational cloud masks in most conditions examined with a few exceptions. The largest improvements we observe occur during the night over snow or ice covered surfaces in the high latitudes. In our analysis, we show that this improvement is not solely due to differences in optical depth-based definitions of a cloud between each mask. We also analyze the differences in true positive rate between day/night and land/water scenes as a function of optical depth. Such differences are a contributor to spatial artifacts in cloud masking and we find that the neural network is the most consistent in cloud detection with respect to optical depth across these conditions. A regional analysis over Greenland illustrates the impact of such differences and shows that they can result in mean cloud fractions with very different spatial and temporal characteristics.

Bolt Tightening Using Impact Wrench Based on Neural Networks

2000 ◽  
Vol 12 (6) ◽  
pp. 706-711
Author(s):  
Toru Fujinaka ◽  
◽  
Hirofumi Nakano ◽  
Michifumi Yoshioka ◽  
Sigeru Omatu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Clamping Force ◽  
The Neural Network ◽  
The Impact

A method for controlling the tightening operation of bolts using an impact wrench is proposed, where the neural network is employed for achieving proper clamping force. The characteristics of the clamping force depend on the kind of work to which bolts are tightened, thus a neural network is used for classification of the work. The clamping force, which can only be measured during the test run, is estimated online, using another neural network. Then appropriate input to the actuator of the impact wrench is determined, based on the estimated value of the clamping force.

scholarly journals Artificial neural network inspired by quantum computing solutions using the movement model of the PR-02 robot

2018 ◽  
Vol 19 ◽  
pp. 01007
Author(s):  
Jerzy Tchórzewski ◽  
Dariusz Ruciński ◽  
Przemysław Domański
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Quantum Computing ◽  
Arm Movement ◽  
Neural Model ◽  
Movement Model ◽  
The Neural Network ◽  
Neural Network Toolbox ◽  
Artificial Neural ◽  
Matrix Quantum

The paper proposes a new method of quantum computing using control and systems theory as well as matrix-quantum computing. The algorithm developed on the basis of the PR-02 robot’s arm’s movement was implemented in using the Neural Network Toolbox. The application of the neural model instead of the analytic model allowed for obtaining the improvement of the trajectory of the PR-02 robot’s arm movement, while the application of the quantum artificial neural network for the assumed number of quasi-parallel computations equal 1000 did not result in the improvement of the model.

scholarly journals A practical demonstration on AMSU retrieval precision for upper tropospheric humidity by a non-linear multi-channel regression method

2005 ◽  
Vol 5 (2) ◽  
pp. 451-459 ◽  
Author(s):  
C. Jiménez ◽  
P. Eriksson ◽  
V. O. John ◽  
S. A. Buehler
Keyword(s):  
Neural Network ◽  
Relative Humidity ◽  
Single Channel ◽  
Weighting Function ◽  
Traditional Approach ◽  
Training Dataset ◽  
The Neural Network ◽  
Radiosonde Station ◽  
Neural Network Algorithm ◽  
The Impact

Abstract. A neural network algorithm inverting selected channels from the Advance Microwave Sounding Unit instruments AMSU-A and AMSU-B was applied to retrieve layer averaged relative humidity. The neural network was trained with a global synthetic dataset representing clear-sky conditions. A precision of around 6% was obtained when retrieving global simulated radiances, the precision deteriorated less than 1% when real mid-latitude AMSU radiances were inverted and compared with co-located data from a radiosonde station. The 6% precision outperforms by 1% the reported precision estimate from a linear single-channel regression between radiance and weighting function averaged relative humidity, the more traditional approach to exploit AMSU data. Added advantages are not only a better precision; the AMSU-B humidity information is more optimally exploited by including temperature information from AMSU-A channels; and the layer averaged humidity is a more physical quantity than the weighted humidity, for comparison with other datasets. The training dataset proved adequate for inverting real radiances from a mid-latitude site, but it is limited by not considering the impact of clouds or surface emissivity changes, and further work is needed in this direction for further validation of the precision estimates.

scholarly journals Spatially-Aware Clustering of Ion Images in Mass Spectrometry Imaging Data Using Deep Learning

2020 ◽  
Author(s):  
Wanqiu Zhang ◽  
Marc Claesen ◽  
Thomas Moerman ◽  
M. Reid Groseclose ◽  
Etienne Waelkens ◽  
...  
Keyword(s):  
Neural Network ◽  
Mass Spectrometry ◽  
Deep Learning ◽  
Mass Spectrometry Imaging ◽  
Spatial Information ◽  
Image Clustering ◽  
Imaging Data ◽  
The Neural Network ◽  
Clustering Quality ◽  
The Impact

AbstractComputational analysis is crucial to capitalize on the wealth of spatio-molecular information generated by mass spectrometry imaging (MSI) experiments. Currently, the spatial information available in MSI data is often under-utilized, due to the challenges of in-depth spatial pattern extraction.The advent of deep learning has greatly facilitated such complex spatial analysis. In this work, we use a pre-trained neural network to extract high-level features from ion images in MSI data, and test whether this improves downstream data analysis. The resulting neural network interpretation of ion images, coined neural ion images, are used to cluster ion images based on spatial expressions.We evaluate the impact of neural ion images on two ion image clustering pipelines, namely DBSCAN clustering, combined with UMAP-based dimensionality reduction, and k-means clustering. In both pipelines, we compare regular and neural ion images from two different MSI datasets. All tested pipelines could extract underlying spatial patterns, but the neural network-based pipelines provided better assignment of ion images, with more fine-grained clusters, and greater consistency in the spatial structures assigned to individual clusters.Additionally, we introduce the Relative Isotope Ratio metric to quantitatively evaluate clustering quality. The resulting scores show that isotopical m/z values are more often clustered together in the neural network-based pipeline, indicating improved clustering outcomes.The usefulness of neural ion images extends beyond clustering towards a generic framework to incorporate spatial information into any MSI-focused machine learning pipeline, both supervised and unsupervised.

Sign in / Sign up

Export Citation Format

Share Document