Conceptual Design of Freeform Surfaces From Unstructured Point Sets Using Neural Network Regression

2011 ◽  
Author(s):  
Mehmet Ersin Yumer ◽  
Levent Burak Kara
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Locally Linear Embedding ◽  
Point Sets ◽  
3D Space ◽  
Closed Surfaces ◽  
Test Models ◽  
Point Set ◽  
Linear Embedding ◽  
Trained Network

This paper presents a new point set surfacing method that employs neural networks for regression. Our technique takes as input unstructured and possibly noisy point sets representing two-manifolds in R3. To facilitate parametrization, the set is first embedded in R2 using neighborhood preserving locally linear embedding. A neural network is then constructed and trained that learns a mapping between the embedded 2D parametric coordinates and the corresponding 3D space coordinates. The trained network is then used to generate a tessellation that spans the parametric space, thereby producing a surface in the original space. This approach enables the surfacing of noisy and non-uniformly distributed point sets, and can be applied to open or closed surfaces. We show the utility of the proposed method on a number of test models, as well as its application to freeform surface creation in virtual reality environments.

Prediction of Hydrodynamic Forces and Moments on Submarines Using Neural Networks

2002 ◽  
Author(s):  
Ibrahim Mohamed ◽  
Mahmoud Haddara ◽  
Christopher D. Williams ◽  
Michael Mackay
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Hydrodynamic Model ◽  
Parametric Identification ◽  
Hydrodynamic Forces ◽  
Degree Of Freedom ◽  
Experimental Time ◽  
Time Histories ◽  
Trained Network ◽  
Identification Tool

This paper describes a parametric identification tool for predicting the hydrodynamic forces acting on a submarine model using its motion history. The tool uses a neural network to identify the hydrodynamic forces and moments; the network was trained with data obtained from multi-degree-of-freedom captive maneuvering tests. The characteristics of the trained network are demonstrated through reconstruction of the force and moment time histories. This technique has the potential to reduce experimental time and cost by enabling a full hydrodynamic model of the vehicle to be obtained from a relatively limited number of test maneuvers.

scholarly journals INVOLUTIONS OF GRAPH LINK EXTERIORS WHOSE FIXED POINT SETS ARE CLOSED SURFACES

2010 ◽  
Vol 81 (2) ◽  
pp. 298-303 ◽  
Author(s):  
TORU IKEDA
Keyword(s):  
Fixed Point ◽  
Lower Estimate ◽  
Closed Surface ◽  
Point Sets ◽  
Fixed Point Set ◽  
Closed Surfaces ◽  
Point Set ◽  
Graph Link ◽  
Fixed Point Sets

AbstractA link L in S3 possibly admits an involution of the exterior E(L) with fixed point set a closed surface, which is not extendable to an involution of S3. In this paper, we focus on the case of graph links and show that the genus of the surface provides a lower estimate of the number of link components.

scholarly journals Task-driven hierarchical deep neural network models of the proprioceptive pathway

2020 ◽  
Author(s):  
Kai J. Sandbrink ◽  
Pranav Mamidanna ◽  
Claudio Michaelis ◽  
Mackenzie Weygandt Mathis ◽  
Matthias Bethge ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Somatosensory Cortex ◽  
Action Recognition ◽  
Large Scale ◽  
Recognition Task ◽  
List Type ◽  
Control Mechanisms ◽  
Neural Network Models ◽  
3D Space

Biological motor control is versatile and efficient. Muscles are flexible and undergo continuous changes requiring distributed adaptive control mechanisms. How proprioception solves this problem in the brain is unknown. Here we pursue a task-driven modeling approach that has provided important insights into other sensory systems. However, unlike for vision and audition where large annotated datasets of raw images or sound are readily available, data of relevant proprioceptive stimuli are not. We generated a large-scale dataset of human arm trajectories as the hand is tracing the alphabet in 3D space, then using a musculoskeletal model derived the spindle firing rates during these movements. We propose an action recognition task that allows training of hierarchical models to classify the character identity from the spindle firing patterns. Artificial neural networks could robustly solve this task, and the networks’ units show directional movement tuning akin to neurons in the primate somatosensory cortex. The same architectures with random weights also show similar kinematic feature tuning but do not reproduce the diversity of preferred directional tuning nor do they have invariant tuning across 3D space. Taken together our model is the first to link tuning properties in the proprioceptive system to the behavioral level.HighlightsWe provide a normative approach to derive neural tuning of proprioceptive features from behaviorally-defined objectives.We propose a method for creating a scalable muscle spindles dataset based on kinematic data and define an action recognition task as a benchmark.Hierarchical neural networks solve the recognition task from muscle spindle inputs.Individual neural network units in middle layers resemble neurons in primate somatosensory cortex & make predictions for neurons along the proprioceptive pathway.

scholarly journals Brick Assembly Networks: An Effective Network for Incremental Learning Problems

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1929
Author(s):  
Jiacang Ho ◽  
Dae-Ki Kang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Language Processing ◽  
Loss Function ◽  
Incremental Learning ◽  
Network Architecture ◽  
High Performance ◽  
Learning Problem ◽  
Output Layer ◽  
Trained Network

Deep neural networks have achieved high performance in image classification, image generation, voice recognition, natural language processing, etc.; however, they still have confronted several open challenges that need to be solved such as incremental learning problem, overfitting in neural networks, hyperparameter optimization, lack of flexibility and multitasking, etc. In this paper, we focus on the incremental learning problem which is related with machine learning methodologies that continuously train an existing model with additional knowledge. To the best of our knowledge, a simple and direct solution to solve this challenge is to retrain the entire neural network after adding the new labels in the output layer. Besides that, transfer learning can be applied only if the domain of the new labels is related to the domain of the labels that have already been trained in the neural network. In this paper, we propose a novel network architecture, namely Brick Assembly Network (BAN), which allows a trained network to assemble (or dismantle) a new label to (or from) a trained neural network without retraining the entire network. In BAN, we train labels with a sub-network (i.e., a simple neural network) individually and then we assemble the converged sub-networks that have trained for a single label together to form a full neural network. For each label to be trained in a sub-network of BAN, we introduce a new loss function that minimizes the loss of the network with only one class data. Applying one loss function for each class label is unique and different from standard neural network architectures (e.g., AlexNet, ResNet, InceptionV3, etc.) which use the values of a loss function from multiple labels to minimize the error of the network. The difference of between the loss functions of previous approaches and the one we have introduced is that we compute a loss values from node values of penultimate layer (we named it as a characteristic layer) instead of the output layer where the computation of the loss values occurs between true labels and predicted labels. From the experiment results on several benchmark datasets, we evaluate that BAN shows a strong capability of adding (and removing) a new label to a trained network compared with a standard neural network and other previous work.

Comparing Different Fitting Strategies for Matching Two 3D Point Sets Using a Multivariable Minimizer

2001 ◽  
Author(s):  
Sander Spanjaard ◽  
Joris S. M. Vergeest
Keyword(s):  
Conceptual Design ◽  
Global Minimum ◽  
Research Question ◽  
Point Sets ◽  
Source Point ◽  
3D Space ◽  
Point Set ◽  
The Mean ◽  
Scan Data ◽  
User Intervention

Abstract Finding the best match of two geometric entities in 3D space is a key stage for purposes such as object recognition and reverse engineering. The reuse of existing freeform shapes during conceptual design is also an application. In this paper we compare different fitting strategies for matching two 3D point sets using a multivariable minimizer. The strategies are evaluated against speed, robustness and correctness of result. The fitting process aims at matching two point sets, a source point set and a template point set. The template point set is translated, rotated but also deformed during the fit, such that it gets placed into the neighborhood of the source point set and gets aligned to it as good as possible. The deformation of the template shape is controlled by shape parameters, which are varied to enhance the match. The engine behind the process is a multivariable function’s global minimum finder. Its objective is to minimize the Mean Directed Hausdorff Distance (MDHD) between the two point sets by altering the parameters of the template point set. One research question was whether or not a fully automated fitting process is feasible with our method. We performed numerical experiments with 3D scan data and a shape template defined by up to 8 free parameters. Four different strategies where used to do the fitting with one of them allowing user intervention. Comparing the strategies on total fit time, minimum MDHD and correctness of result a conclusion is drawn which strategy gives the highest chance on the best results. The relevance of the technology for shape reuse in conceptual design is also discussed.

scholarly journals Specificities of data set preparation and neural network training for object recognition

2021 ◽  
pp. 146-151
Author(s):  
Dmytro Kyrychuk ◽  
Andriy Segin
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Recognition ◽  
Neural Network Training ◽  
Data Set ◽  
Network Training ◽  
Object Based ◽  
Recognition Ability ◽  
Trained Network

The paper presents the results of the research on the expediency of training a neural network on images of different clarity and brightness using unevenly distributed lighting on a working area with statically positioned system elements. The use of transfer learning for neural networks to improve the accuracy of object recognition was justified. The object recognition ability of a convolutional neural network while scaling the object relatively to the original was researched. The results of the research on the influence of lighting on the quality of object recognition by a trained network and the influence of background choice for a working area on the quality of object-based feature selection are presented. Based on the results obtained, recommendations for the preparation of individual datasets to improve the quality of training and further object recognition of convolutional neural networks through the elimination of unnecessary variables in images were provided.

Sign in / Sign up

Export Citation Format

Share Document