How do machines learn? Evaluating the AIcon2abs method

• URL: http://arxiv.org/abs/2401.07386v3
• Date: Wed, 24 Jul 2024 15:57:40 GMT
• Title: How do machines learn? Evaluating the AIcon2abs method
• Authors: Rubens Lacerda Queiroz, Cabral Lima, Fabio Ferrentini Sampaio, Priscila Machado Vieira Lima,
• Abstract summary: This paper evaluates AI from concrete to Abstract (AIcon2abs), a recently proposed method that enables awareness among the general public on machine learning. The WiSARD model does not require an Internet connection for training and classification, and it can learn from a few or one example. The AIcon2abs method's effectiveness was assessed through the evaluation of a remote course with a workload of approximately 6 hours.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper evaluates AI from concrete to Abstract (AIcon2abs), a recently proposed method that enables awareness among the general public on machine learning. Such is possible due to the use of WiSARD, an easily understandable machine learning mechanism, thus requiring little effort and no technical background from the target users. WiSARD is adherent to digital computing; training consists of writing to RAM-type memories, and classification consists of reading from these memories. The model enables easy visualization and understanding of training and classification tasks' internal realization through ludic activities. Furthermore, the WiSARD model does not require an Internet connection for training and classification, and it can learn from a few or one example. WiSARD can also create "mental images" of what it has learned so far, evidencing key features pertaining to a given class. The AIcon2abs method's effectiveness was assessed through the evaluation of a remote course with a workload of approximately 6 hours. It was completed by thirty-four Brazilian subjects: 5 children between 8 and 11 years old; 5 adolescents between 12 and 17 years old; and 24 adults between 21 and 72 years old. The collected data was analyzed from two perspectives: (i) from the perspective of a pre-experiment (of a mixed methods nature) and (ii) from a phenomenological perspective (of a qualitative nature). AIcon2abs was well-rated by almost 100% of the research subjects, and the data collected revealed quite satisfactory results concerning the intended outcomes. This research has been approved by the CEP/HUCFF/FM/UFRJ Human Research Ethics Committee.

Related papers

• Detecting Unsuccessful Students in Cybersecurity Exercises in Two Different Learning Environments [0.37729165787434493]
  This paper develops automated tools to predict when a student is having difficulty. In a potential application, such models can aid instructors in detecting struggling students and providing targeted help.
  arXiv  Detail & Related papers  (2024-08-16T04:57:54Z)
• Adversarial Machine Unlearning [26.809123658470693]
  This paper focuses on the challenge of machine unlearning, aiming to remove the influence of specific training data on machine learning models. Traditionally, the development of unlearning algorithms runs parallel with that of membership inference attacks (MIA), a type of privacy threat. We propose a game-theoretic framework that integrates MIAs into the design of unlearning algorithms.
  arXiv  Detail & Related papers  (2024-06-11T20:07:22Z)
• Is my Data in your AI Model? Membership Inference Test with Application to Face Images [18.402616111394842]
  This article introduces the Membership Inference Test (MINT), a novel approach that aims to empirically assess if given data was used during the training of AI/ML models. We propose two MINT architectures designed to learn the distinct activation patterns that emerge when an Audited Model is exposed to data used during its training process. Experiments are carried out using six publicly available databases, comprising over 22 million face images in total.
  arXiv  Detail & Related papers  (2024-02-14T15:09:01Z)
• Deep Learning-based Spatio Temporal Facial Feature Visual Speech Recognition [0.0]
  We present an alternate authentication process that makes use of both facial recognition and the individual's distinctive temporal facial feature motions while they speak a password. The suggested model attained an accuracy of 96.1% when tested on the industry-standard MIRACL-VC1 dataset.
  arXiv  Detail & Related papers  (2023-04-30T18:52:29Z)
• ALBench: A Framework for Evaluating Active Learning in Object Detection [102.81795062493536]
  This paper contributes an active learning benchmark framework named as ALBench for evaluating active learning in object detection. Developed on an automatic deep model training system, this ALBench framework is easy-to-use, compatible with different active learning algorithms, and ensures the same training and testing protocols.
  arXiv  Detail & Related papers  (2022-07-27T07:46:23Z)
• Few-Cost Salient Object Detection with Adversarial-Paced Learning [95.0220555274653]
  This paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only. We name this task as the few-cost salient object detection and propose an adversarial-paced learning (APL)-based framework to facilitate the few-cost learning scenario.
  arXiv  Detail & Related papers  (2021-04-05T14:15:49Z)
• Personalized Education in the AI Era: What to Expect Next? [76.37000521334585]
  The objective of personalized learning is to design an effective knowledge acquisition track that matches the learner's strengths and bypasses her weaknesses to meet her desired goal. In recent years, the boost of artificial intelligence (AI) and machine learning (ML) has unfolded novel perspectives to enhance personalized education.
  arXiv  Detail & Related papers  (2021-01-19T12:23:32Z)
• NavRep: Unsupervised Representations for Reinforcement Learning of Robot Navigation in Dynamic Human Environments [28.530962677406627]
  We train two end-to-end, and 18 unsupervised-learning-based architectures, and compare them, along with existing approaches, in unseen test cases. Our results show that unsupervised learning methods are competitive with end-to-end methods. This release also includes OpenAI-gym-compatible environments designed to emulate the training conditions described by other papers.
  arXiv  Detail & Related papers  (2020-12-08T12:51:14Z)
• A robot that counts like a child: a developmental model of counting and pointing [69.26619423111092]
  A novel neuro-robotics model capable of counting real items is introduced. The model allows us to investigate the interaction between embodiment and numerical cognition. The trained model is able to count a set of items and at the same time points to them.
  arXiv  Detail & Related papers  (2020-08-05T21:06:27Z)
• Symbiotic Adversarial Learning for Attribute-based Person Search [86.7506832053208]
  We present a symbiotic adversarial learning framework, called SAL.Two GANs sit at the base of the framework in a symbiotic learning scheme. Specifically, two different types of generative adversarial networks learn collaboratively throughout the training process.
  arXiv  Detail & Related papers  (2020-07-19T07:24:45Z)
• Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experience [76.9910678786031]
  We propose a novel paradigm of explainable active learning (XAL), by introducing techniques from the recently surging field of explainable AI (XAI) into an Active Learning setting. Our study shows benefits of AI explanation as interfaces for machine teaching--supporting trust calibration and enabling rich forms of teaching feedback, and potential drawbacks--anchoring effect with the model judgment and cognitive workload.
  arXiv  Detail & Related papers  (2020-01-24T22:52:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.