Filters








98,338 Hits in 4.6 sec

Modeling reverse thinking for machine learning [article]

Li Huihui, Wen Guihua
2018 arXiv   pre-print
Because all machine learning methods do not consider illusion inertial thinking, in this paper we propose a new method that uses reverse thinking to correct illusion inertial thinking, which increases  ...  Similarly, machine learning methods also form inertial thinking schemes through learning the knowledge from a large amount of data.  ...  However, for machine learning methods, reverse thinking is totally not considered.  ... 
arXiv:1803.00158v1 fatcat:4uheegwxujhsnohwo7bfnacpt4

Bi-directional Cognitive Thinking Network for Machine Reading Comprehension [article]

Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Jing Yu, Yajing Sun, Xiangpeng Wei
2020 arXiv   pre-print
The model has the ability to reverse reasoning questions which can assist inertial thinking to generate more accurate answers.  ...  We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory.  ...  Acknowledgements We thank all anonymous reviewers for their constructive comments. This work is supported by the National Natural Science Foundation of China (No.62006222).  ... 
arXiv:2010.10286v1 fatcat:r6i3co2xqvemnpj5irqcnjthoa

Use of Models in Reverse Thinking

Romans Vitkovskis, Uldis Heidingers
2018 US-China Education Review. B  
For this purpose, reverse thinking is the useful as described in this paper.  ...  If he/she had reverse thinking, he/she could use a model to explain how his/her washing machine works as well as why his/her relationship with wife is getting weaker.  ...  Learning Reverse Thinking Reverse thinking cannot be obtained by learning it as a school subject.  ... 
doi:10.17265/2161-6248/2018.02.003 fatcat:a5aijnovtvcmhge6keryightrm

Machines Imitating Human Thinking Using Bayesian Learning and Bootstrap

Sunghae Jun
2021 Symmetry  
Bayesian learning such as this also provides an optimal decision; thus, this is not well-suited to the modeling of thinking machines.  ...  However, humans sometimes think and act not optimally but emotionally. In this paper, we propose a method for building thinking machines imitating humans using Bayesian decision theory and learning.  ...  Bayesian Learning for Human Behaviors In this paper, we consider the Bayesian inference procedure to build a Bayesian learning model for thinking machines.  ... 
doi:10.3390/sym13030389 fatcat:fyyffwdiibbidjys676o62klde

Believing in one's power: a counterfactual heuristic for goal-directed control [article]

Valerian Chambon, Heloise Thero, Charles Findling, Etienne Koechlin
2018 bioRxiv   pre-print
We suggest that our model outperformed all competitors because it closely mirrors people's belief in their causal power - a belief that is well-suited to learning action-outcome associations in controllable  ...  This ability to monitor one's own causal power has long been suggested to rest upon a specific model of causal inference, i.e., a model of how our actions causally relate to their consequences.  ...  Acknowledgments We thank Valentin Wyart and Stefano Palminteri for comments and useful discussions about earlier versions of this manuscript.  ... 
doi:10.1101/498675 fatcat:xbpyxem6hvdsbduoyiob4n7o7u

Sentiment Classification Considering Negation and Contrast Transition

Shoushan Li, Chu-Ren Huang
2009 Pacific Asia Conference on Language, Information and Computation  
The experimental results show that incorporating both negation and contrast transition information is effective and performs robustly better than traditional machine learning approach (based on one-bag-of-words  ...  modeling) across five different domains.  ...  of those machine learning approaches based on one-bag-of-words modeling.  ... 
dblp:conf/paclic/LiH09 fatcat:6krbns5tbrcwdmamqer5dstlmq

Neural Recall Network: A Neural Network Solution to Low Recall Problem in Regex-based Qualitative Coding

Zhiqiang Cai, Cody Marquart, David Shaffer, Antonija Mitrovic, Nigel Bosch
2022 Zenodo  
Based on this finding, we propose an interactive coding mechanism in which human-developed regex classifiers provide input for training machine learning algorithms and machine learning algorithms "smartly  ...  We randomly constructed incomplete (partial) regex lists and used neural network models to identify negative reversion sets in which the frequency of false negatives increased from a range of 3\\%-8\\%  ...  This work was funded in part by the National Science Foundation (DRL-1713110, DRL-2100320,LDI-1934745), the Wisconsin Alumni Research Foundation, and the Office of the Vice Chancellor for Research and  ... 
doi:10.5281/zenodo.6853046 fatcat:hft36zoeh5bfxal7d3bqj6rwte

AI minds need to think about energy constraints

Indrė Žliobaitė
2019 Nature Machine Intelligence  
This is implied to be similar to reinforcement learning in reverse, or, perhaps, meta-reinforcement learning: an AI could infer the objectives of the rewarder by observing their rewards.  ...  A suggestive resolution emerges from multiple essays -instead of providing explicit learning objectives for AI, could the way forward be to learn these objectives from examples?  ... 
doi:10.1038/s42256-019-0083-7 fatcat:4nnbjm2arnfq3j2t7wel6l6cva

Bayesian Neural Networks for Reversible Steganography [article]

Ching-Chun Chang
2022 arXiv   pre-print
Recent advances in deep learning have led to a paradigm shift in reversible steganography.  ...  A fundamental pillar of reversible steganography is predictive modelling which can be realised via deep neural networks.  ...  INTRODUCTION A RTIFICIAL intelligence arises from the question 'Can machines think?' [1] . Machine learning refocuses attention on addressing solvable problems of a practical nature automatically.  ... 
arXiv:2201.02478v1 fatcat:3sgon3ktundc5pfqqzixdddhxa

Categories of Differentiable Polynomial Circuits for Machine Learning [article]

Paul Wilson, Fabio Zanasi
2022 arXiv   pre-print
Reverse derivative categories (RDCs) have recently been shown to be a suitable semantic framework for studying machine learning algorithms.  ...  In particular, we propose polynomial circuits as a suitable machine learning model. We give an axiomatisation for these circuits and prove a functional completeness result.  ...  This property, which we call 'functional completeness', is important for a class of machine learning models to satisfy because it guarantees that we may always construct an appropriate model for a given  ... 
arXiv:2203.06430v2 fatcat:6mpunzhlxjc7nndr36y6is3xxm

Pedagogical strategies for enhancing machine design teaching in a mechanical technology programme
Inglés

Carlos A. Romero-Piedrahita, Libardo V. Vanegas-Useche, Miguel Díaz Rodríguez
2019 Revista UIS Ingenierías  
Active learning, hands-on activities, laboratory sessions, practical examples, projects, teamwork and technological and virtual resources are used as a means to achieve effectively the learning outcomes  ...  The aim of this paper is to present a reformed approach to the teaching practice of the Machine Design course offered in the Mechanical Technology Programme at the Technological University of Pereira.  ...  This was done to gain an insight into the evolving pedagogical models and the variables affecting the teaching of machine design and also, to construct a pedagogical framework for the course of Machine  ... 
doi:10.18273/revuin.v18n3-2019001 fatcat:xwxkq3xwibdhvfhmnnimvihwye

REVERSE ENGINEERING FOR ARTIFICIAL INTELLIGENCE TO PREVENT HEALTHCARE OF HUMAN BRAIN

2021 International Journal of Biology Pharmacy and Allied Sciences  
Therapy of cognitive impairment, academic interest in awareness and the human healthcare condition, a lower part method to creating thinking machines, and archives of all neuroscience research findings  ...  Reverse engineering is a popular method of simulating the human mind on a molecular basis.  ...  Machine Learning is the backbone of Blue Mind, a science that creates intelligent devices and distributes smart machines.  ... 
doi:10.31032/ijbpas/2021/10.11.1116 fatcat:bc3mottmqfeivoc6yp3em4dvbm

Artificial Brain Based on Credible Neural Circuits in a Human Brain [article]

John Robert Burger
2010 arXiv   pre-print
State machines, assumed previously learned in subconscious associative memory are shown to enable equation solving and rudimentary thinking using nanoprocessing within short term memory.  ...  involving recalling, thinking and learning.  ...  Artificial brains, as in models of biological brains, have learning in the form of an embedded state machine within long term memory (Burger, Sept 5, 2010) .  ... 
arXiv:1008.5161v3 fatcat:j4o2ac7sjbbxxenr6phupose3u

MODERN AREAS OF COMPUTATIONAL LINGUISTICS
KOMPÜTER DİLÇİLİYİNİN MÜASIR İSTİQAMƏTLƏRİ

Kamila Valiyeva
2016 Problems of Information Society  
machine translation issues.  ...  The paper analyzes the main trends of computer linguistics -natural language processing, corpus linguistics, computer-aided dictionary compiling, computer-aided learning and recognition of languages, including  ...  Machine learning -a branch of artificial intelligence aimed at teaching and developing algorithm models.  ... 
doi:10.25045/jpis.v07.i2.10 fatcat:jscmwsfvunawzbrjcfnzlq56iu

Multi-disciplinary approach in engineering education: learning with additive manufacturing and reverse engineering

Andrea Gatto, Elena Bassoli, Lucia Denti, Luca Iuliano, Paolo Minetola, Dr Eujin Pei
2015 Rapid prototyping journal  
A digital head model is reverse engineered from an anatomical mannequin and used as an ergonomic mock-up. The project includes prototype testing and cost analysis.  ...  The device is produced using additive manufacturing techniques for hands-on evaluation by the students.  ...  Students are asked to design the head mount by using a digital head model, obtained by reverse engineering a mannequin for anatomical studies.  ... 
doi:10.1108/rpj-09-2014-0134 fatcat:7jfgc5gya5c2hgp2c743bgtsne
« Previous Showing results 1 — 15 out of 98,338 results