Combination rules in multiple cue probability learning: I. Relation to task characteristics and performance.

1976 ◽  
Author(s):  
Bengt-Ake Armelius ◽  
Kerstin Armelius
Keyword(s):  
Probability Learning ◽  
Task Characteristics ◽  
Combination Rules ◽  
And Performance

scholarly journals Road Characteristics Detection Based on Joint Convolutional Neural Networks with Adaptive Squares

2021 ◽  
Vol 10 (6) ◽  
pp. 377
Author(s):  
Chiao-Ling Kuo ◽  
Ming-Hua Tsai
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Autonomous Vehicles ◽  
Detection Accuracy ◽  
Geospatial Information ◽  
Combination Rules ◽  
And Performance ◽  
Road Characteristics ◽  
Machine Readable ◽  
Background Image

The importance of road characteristics has been highlighted, as road characteristics are fundamental structures established to support many transportation-relevant services. However, there is still huge room for improvement in terms of types and performance of road characteristics detection. With the advantage of geographically tiled maps with high update rates, remarkable accessibility, and increasing availability, this paper proposes a novel simple deep-learning-based approach, namely joint convolutional neural networks (CNNs) adopting adaptive squares with combination rules to detect road characteristics from roadmap tiles. The proposed joint CNNs are responsible for the foreground and background image classification and various types of road characteristics classification from previous foreground images, raising detection accuracy. The adaptive squares with combination rules help efficiently focus road characteristics, augmenting the ability to detect them and provide optimal detection results. Five types of road characteristics—crossroads, T-junctions, Y-junctions, corners, and curves—are exploited, and experimental results demonstrate successful outcomes with outstanding performance in reality. The information of exploited road characteristics with location and type is, thus, converted from human-readable to machine-readable, the results will benefit many applications like feature point reminders, road condition reports, or alert detection for users, drivers, and even autonomous vehicles. We believe this approach will also enable a new path for object detection and geospatial information extraction from valuable map tiles.

scholarly journals Promoting creativity and innovation: expected and unexpected consequences

2019 ◽  
Vol 13 (3) ◽  
pp. 296-310 ◽  
Author(s):  
Thi Hong Nguyen ◽  
Angelina Nhat-Hanh Le
Keyword(s):  
Unethical Behavior ◽  
Structural Equation ◽  
Path Model ◽  
Equation Modeling ◽  
Task Characteristics ◽  
Content Type ◽  
And Performance ◽  
Creativity And Innovation ◽  
Unexpected Consequences

Purpose The paper aims to explore the role of climate for creativity and innovation as the situational variable to lead to both expected and unexpected consequences (e.g. performance and unethical behavior), by discovering the relationships among task characteristics (e.g. difficulty, clarity and performance pressure), individual psychological aspects (e.g. mindfulness and self-justification) and work environmental conditions (e.g. peer behavior and climate for creativity and innovation). In this study, task characteristics are proposed to positively associate with unethical behavior via mindfulness. Moreover, climate for creativity and innovation is proposed to moderate the relationship between self-justification and unethical behavior. Finally, unethical behavior is predicted to positively influence on performance. Design/methodology/approach Data were collected from the sample of salespeople, who are working for variety of companies in Vietnam. Partial least squares structural equation modeling (PLS-SEM) and SmartPLS 3 are implemented to test the path model. Findings Emphasizing both bright and dark sides of promoting creativity and innovation, the study highlights the role of climate for creativity and innovation in strengthening the positive relationship between self-justification and unethical behavior. In turn, unethical behavior positively influences performance. Further, the findings indicate that mindfulness contributes in explaining unconscious unethical behavior. Originality/value Exploring the relationships among climate for creativity and innovation, unethical behavior and performance, this paper contributes for deeper understanding of variety aspects of innovation. Demands for an intelligent management in modern workplaces are suggested.

Effects of Internal and External Control of Reinforcement on Binary-Choice Probability Learning

1972 ◽  
Vol 30 (1) ◽  
pp. 255-260
Author(s):  
Marion Jacobs ◽  
Norman Tiber
Keyword(s):  
Probability Learning ◽  
Personal Control ◽  
Learning Task ◽  
External Control ◽  
Binary Choice ◽  
Choice Probability ◽  
Frequent Event ◽  
The Difference ◽  
And Performance ◽  
The Relationship

This study investigated the relationship between belief in one's ability to control reinforcements and performance in a binary-choice probability-learning situation under varying conditions of risk. The probability-learning task required S repeatedly to predict whether a red or green bulb would light up next. Red was programmed to occur 75% of the time. The sequence was random and not contingent upon Ss' responses. Rotter's Internal-External scale was used to select Ss who generally believed reinforcements were affected by their own behavior (internals) to compare with individuals who believed that most reinforcements were beyond personal control (externals). The conditions of risk were no-payoff, win or lose, win or break even, lose or break even, and reverse (lose for a correct guess and break even for an incorrect one). Performance on the reverse condition differed from all others, with Ss selecting the objectively more frequent event significantly less often. The difference resulted from the behavior of male externals and female internals, who predicted the less frequent event to avoid loss of chips. This is discussed within the framework of social learning theory.

scholarly journals On the Potential of Taxonomic Graphs to Improve Applicability and Performance for the Classification of Biomedical Patents

2021 ◽  
Vol 11 (2) ◽  
pp. 690
Author(s):  
Kai Frerich ◽  
Mark Bukowski ◽  
Sandra Geisler ◽  
Robert Farkas
Keyword(s):  
Technology Management ◽  
Classification Performance ◽  
Ensemble Classification ◽  
Combination Rules ◽  
Patent Classification ◽  
Tree Graphs ◽  
Fusion Methods ◽  
And Performance ◽  
Artificial Neural Network Ann

A core task in technology management in biomedical engineering and beyond is the classification of patents into domain-specific categories, increasingly automated by machine learning, with the fuzzy language of patents causing particular problems. Striving for higher classification performance, increasingly complex models have been developed, based not only on text but also on a wealth of distinct (meta) data and methods. However, this makes it difficult to access and integrate data and to fuse distinct predictions. Although the already established Cooperate Patent Classification (CPC) offers a plethora of information, it is rarely used in automated patent categorization. Thus, we combine taxonomic and textual information to an ensemble classification system comparing stacking and fixed combination rules as fusion methods. Various classifiers are trained on title/abstract and on both the CPC and IPC (International Patent Classification) assignments of 1230 patents covering six categories of future biomedical innovation. The taxonomies are modeled as tree graphs, parsed and transformed by Dissimilarity Space Embedding (DSE) to real-valued vectors. The classifier ensemble tops the basic performance by nearly 10 points to F1 = 78.7% when stacked with a feed-forward Artificial Neural Network (ANN). Taxonomic base classifiers perform nearly as well as the text-based learners. Moreover, an ensemble only of CPC and IPC learners reaches F1 = 71.2% as fully language independent and straightforward approach of established algorithms and readily available integrated data enabling new possibilities for technology management.

Sign in / Sign up

Export Citation Format

Share Document