scholarly journals Autonomously Learning About Meaningful Actions from Exploratory Behaviour

2021 ◽  
Author(s):  
◽  
Heidi Newton
Keyword(s):  
New Method ◽  
Exploratory Behaviour ◽  
Autonomous Agent ◽  
Apriori Algorithm ◽  
Learning Problem ◽  
Human Infants ◽  
Alternative Design ◽  
Learning Tasks ◽  
Learning Rules ◽  
Motor Actions

<p>The thesis addresses the problem of creating an autonomous agent that is able to learn about and use meaningful hand motor actions in a simulated world with realistic physics, in a similar way to human infants learning to control their hand. A recent thesis by Mugan presented one approach to this problem using qualitative representations, but suffered from several important limitations. This thesis presents an alternative design that breaks the learning problem down into several distinct learning tasks. It presents a new method for learning rules about actions based on the Apriori algorithm. It also presents a planner inspired by infants that can use these rules to solve a range of tasks. Experiments showed that the agent was able to learn meaningful rules and was then able to successfully use them to achieve a range of simple planning tasks.</p>

scholarly journals Autonomously Learning About Meaningful Actions from Exploratory Behaviour

2021 ◽  
Author(s):  
◽  
Heidi Newton
Keyword(s):  
New Method ◽  
Exploratory Behaviour ◽  
Autonomous Agent ◽  
Apriori Algorithm ◽  
Learning Problem ◽  
Human Infants ◽  
Alternative Design ◽  
Learning Tasks ◽  
Learning Rules ◽  
Motor Actions

<p>The thesis addresses the problem of creating an autonomous agent that is able to learn about and use meaningful hand motor actions in a simulated world with realistic physics, in a similar way to human infants learning to control their hand. A recent thesis by Mugan presented one approach to this problem using qualitative representations, but suffered from several important limitations. This thesis presents an alternative design that breaks the learning problem down into several distinct learning tasks. It presents a new method for learning rules about actions based on the Apriori algorithm. It also presents a planner inspired by infants that can use these rules to solve a range of tasks. Experiments showed that the agent was able to learn meaningful rules and was then able to successfully use them to achieve a range of simple planning tasks.</p>

scholarly journals Adult's Eyes Trigger Shifts of Visual Attention in Human Infants

1998 ◽  
Vol 9 (2) ◽  
pp. 131-134 ◽  
Author(s):  
Bruce M. Hood ◽  
J. Douglas Willen ◽  
Jon Driver
Keyword(s):  
Visual Attention ◽  
Joint Attention ◽  
New Method ◽  
Attention Shift ◽  
Gaze Perception ◽  
Human Infants ◽  
Young Infants ◽  
The Face ◽  
Attention Shifts

Two experiments examined whether infants shift their visual attention in the direction toward which an adult's eyes turn. A computerized modification of previous joint-attention paradigms revealed that infants as young as 3 months attend in the same direction as the eyes of a digitized adult face. This attention shift was indicated by the latency and direction of their orienting to peripheral probes presented after the face was extinguished. A second experiment found a similar influence of direction of perceived gaze, but also that less peripheral orienting occurred if the central face remained visible during presentation of the probe. This may explain why attention shifts triggered by gaze perception have been difficult to observe in infants using previous naturalistic procedures. Our new method reveals both that direction of perceived gaze can be discriminated by young infants and that this perception triggers corresponding shifts of their own attention.

scholarly journals Association Rules Mining for Hospital Readmission: A Case Study

Mathematics ◽  
2021 ◽  
Vol 9 (21) ◽  
pp. 2706
Author(s):  
Nor Hamizah Miswan ◽  
‘Ismat Mohd Sulaiman ◽  
Chee Seng Chan ◽  
Chong Guan Ng
Keyword(s):  
Association Rule ◽  
Hospital Readmission ◽  
Association Rule Mining ◽  
Demographic Variables ◽  
Apriori Algorithm ◽  
Age Group ◽  
Rule Mining ◽  
Learning Rules ◽  
And Performance

As an indicator of healthcare quality and performance, hospital readmission incurs major costs for healthcare systems worldwide. Understanding the relationships between readmission factors, such as input features and readmission length, is challenging following intricate hospital readmission procedures. This study discovered the significant correlation between potential readmission factors (threshold of various settings for readmission length) and basic demographic variables. Association rule mining (ARM), particularly the Apriori algorithm, was utilised to extract the hidden input variable patterns and relationships among admitted patients by generating supervised learning rules. The mined rules were categorised into two outcomes to comprehend readmission data; (i) the rules associated with various readmission length and (ii) several expert-validated variables related to basic demographics (gender, race, and age group). The extracted rules proved useful to facilitate decision-making and resource preparation to minimise patient readmission.

Proposal of PSwithEFP and its Evaluation in Multi-Agent Reinforcement Learning

2017 ◽  
Vol 21 (5) ◽  
pp. 930-938 ◽  
Author(s):  
Kazuteru Miyazaki ◽  
Koudai Furukawa ◽  
Hiroaki Kobayashi ◽  
◽  
◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Failure Probability ◽  
Action Selection ◽  
New Method ◽  
Selection Strategy ◽  
Multiple Agents ◽  
Learning Problem ◽  
Concurrent Learning ◽  
Multi Agent

When multiple agents learn a task simultaneously in an environment, the learning results often become unstable. This problem is known as the concurrent learning problem and to date, several methods have been proposed to resolve it. In this paper, we propose a new method that incorporates expected failure probability (EFP) into the action selection strategy to give agents a kind of mutual adaptability. The effectiveness of the proposed method is confirmed using Keepaway task.

Novelty and Complexity in Human Infants' Exploratory Behaviour

1998 ◽  
Vol 86 (2) ◽  
pp. 698-698 ◽  
Author(s):  
Santosh Kumar Sahoo
Keyword(s):  
Exploratory Behaviour ◽  
Complex Stimulus ◽  
Human Infants

The effect of novel and complex stimulus cubes on the exploratory behaviour of human infants was analysed in two studies ( ns = 30 and 20). Infants showed relatively greater preference for complex patterned cubes, and their exploratory behaviour habituated over 5 days.

scholarly journals A New Rymon Tree Based Procedure for Mining Statistically Significant Frequent Itemsets

2010 ◽  
Vol 5 (4) ◽  
pp. 567 ◽  
Author(s):  
Predrag Stanisic ◽  
Savo Tomovic
Keyword(s):  
Frequent Itemsets ◽  
Special Structure ◽  
New Method ◽  
Apriori Algorithm ◽  
Support Measure ◽  
Join Algorithm ◽  
Frequent Itemsets Mining

In this paper we suggest a new method for frequent itemsets mining, which is more efficient than well known Apriori algorithm. The method is based on special structure called Rymon tree. For its implementation, we suggest modified sort-merge-join algorithm. Finally, we explain how support measure, which is used in Apriori algorithm, gives statistically significant frequent itemsets.

Cross Sellingusing Association Rule Mining

2014 ◽  
Vol 687-691 ◽  
pp. 1337-1341
Author(s):  
Ran Bo Yao ◽  
An Ping Song ◽  
Xue Hai Ding ◽  
Ming Bo Li
Keyword(s):  
Association Rules ◽  
Association Rule ◽  
Association Rule Mining ◽  
New Method ◽  
Experimental Result ◽  
Apriori Algorithm ◽  
Rule Mining ◽  
Frequent Item ◽  
Direct Benefits ◽  
Frequent Item Sets

In the retail enterprises, it is an important problem to choose goods group through their sales record.We should consider not only the direct benefits of product, but also the benefits bring by the cross selling. On the base of the mutual promotion in cross selling, in this paper we propose a new method to generate the optimal selected model. Firstly we use Apriori algorithm to obtain the frequent item sets and analyses the association rules sets between products.And then we analyses the above results to generate the optimal products mixes and recommend relationship in cross selling. The experimental result shows the proposed method has some practical value to the decisions of cross selling.

scholarly journals Exploratory behaviour towards novel objects is associated with enhanced learning in young horses

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Janne Winther Christensen ◽  
Line Peerstrup Ahrendt ◽  
Jens Malmkvist ◽  
Christine Nicol
Keyword(s):  
Cognitive Abilities ◽  
Intrinsic Factor ◽  
Learning Performance ◽  
Exploratory Behaviour ◽  
The Novel ◽  
Novel Object ◽  
Learning Tasks ◽  
Novel Objects ◽  
Young Horses ◽  
The Impact

AbstractThe mechanisms underlying individual variation in learning are key to understanding the development of cognitive abilities. In humans and primates, curiosity has been suggested as an important intrinsic factor that enhances learning, whereas in domesticated species research has primarily identified factors with a negative effect on cognitive abilities, such as stress and fearfulness. This study presents the first evidence of a link between object-directed curiosity and learning performance in young horses in two very different learning tasks (visual discrimination and pressure-release). We exposed young horses (n = 44) to standardised novel object tests at 5 months and 1 year of age and found consistency in responses. Standard indicators of fearfulness (e.g. heart rate and alertness) were unrelated to learning performance, whereas exploratory behaviour towards the novel objects correlated to performance in both learning tasks. Exploratory behaviour was unreinforced in the novel object tests and likely reflects the animal’s intrinsic motivation (i.e. curiosity), suggesting that this trait is favourable for learning performance. In addition to the insights that these results provide into cognition in a domesticated species, they also raise questions in relation to fostering of curiosity in animals and the impact that such manipulation may have on cognitive abilities.

Sign in / Sign up

Export Citation Format

Share Document