Human-Like Rule Learning from Images Using One-Shot Hypothesis Derivation

Varghese, Dany; Bauer, Roman; Baxter-Beard, Daniel; Muggleton, Stephen; Tamaddoni‐Nezhad, Alireza

doi:10.1007/978-3-030-97454-1_17

Cited by 6 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the approach described in [25], we evaluate the performance of the Siamese network and compare the results with our one-shot learning approach using Metagol. The training data for both systems are one positive example and one or more negative examples (examples from other categories) and the test data is the same as the one used in the previous section.…”

Section: Experiments Comparing Mil With Deep Learningmentioning

confidence: 99%

Towards One-Shot Learning for Text Classification using Inductive Logic Programming

Afroozi Milani,

Cyrus,

Tamaddoni-Nezhad

2023

Electron. Proc. Theor. Comput. Sci.

Self Cite

View full text Add to dashboard Cite

With the ever-increasing potential of AI to perform personalised tasks, it is becoming essential to develop new machine learning techniques which are data-efficient and do not require hundreds or thousands of training data. In this paper, we explore an Inductive Logic Programming approach for one-shot text classification. In particular, we explore the framework of Meta-Interpretive Learning (MIL), along with using common-sense background knowledge extracted from ConceptNet. Results indicate that MIL can learn text classification rules from a small number of training examples, even one example. Moreover, the higher complexity of chosen example for one-shot learning, the higher accuracy of the outcome. Finally, we utilise two approaches, Background Knowledge Splitting and Average One-Shot Learning, to evaluate our model on a public News Category dataset. The outcomes validate MIL's superior performance to the Siamese net for one-shot learning from text.

show abstract

Section: Experiments Comparing Mil With Deep Learningmentioning

confidence: 99%

Towards One-Shot Learning for Text Classification using Inductive Logic Programming

Afroozi Milani,

Cyrus,

Tamaddoni-Nezhad

2023

Electron. Proc. Theor. Comput. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Background knowledge is used together with examples to induce a hypothesis, in the form of a logic program, describing positive and negative examples in given data. ILP is applied to, e.g., scientific discovery, robotics, program analysis (Cropper et al, 2022), with neurosymbolic approaches to machine vision problems (Dai et al, 2015;Varghese et al, 2021).…”

Section: Related Workmentioning

confidence: 99%

An Algebraic Approach to Learning and Grounding

Björklund¹,

Lindström²,

Drewes³

2022

Preprint

View full text Add to dashboard Cite

We consider the problem of learning the semantics of composite algebraic expressions from examples. The outcome is a versatile framework for studying learning tasks that can be put into the following abstract form: The input is a partial algebra A and a finite set of samples (ϕ 1 , O 1 ), (ϕ 2 , O 2 ), . . ., each consisting of an algebraic term ϕ i and a set of objects O i . The objective is to simultaneously fill in the missing algebraic operations in A and ground the variables of every ϕ i in O i , so that the combined value of the terms is optimised. We demonstrate the applicability of this framework through case studies in grammatical inference, picture-language learning, and the grounding of logic scene descriptions.

show abstract

“…Using the George Washington data set and a data set consisting of Indian city names, a success rate of 92.4% was achieved with five shots. The basic one-shot hypothesis derivation (OSHD) approach developed by Varghese et al (2021) was tested on two challenging computer vision tasks, Malayalam character recognition and diagnosis from retinal images, and the results were compared with those using the SNN. As a result, it has been observed that the proposed OSHD method gives better results than SNN.…”

Section: Introductionmentioning

confidence: 99%

Roof type classification with innovative machine learning approaches

Ölçer¹,

Ölçer²,

Sümer³

2023

PeerJ Computer Science

View full text Add to dashboard Cite

Recently, convolutional neural network-based methods have been used extensively for roof type classification on images taken from space. The most important problem with classification processes using these methods is that it requires a large amount of training data. Usually, one or a few images are enough for a human to recognise an object. The one-shot learning approach, like the human brain, aims to effect learning about object categories with just one or a few training examples per class, rather than using huge amounts of data. In this study, roof-type classification was carried out with a few training examples using the one-time learning approach and the so-called Siamese neural network method. The images used for training were artificially produced due to the difficulty of finding roof data. A data set consisting of real roof images was used for the test. The test and training data set consisted of three different types: flat, gable and hip. Finally, a convolutional neural network-based model and a Siamese neural network model were trained with the same data set and the test results were compared with each other. When testing the Siamese neural network model, which was trained with artificially produced images, with real roof images, an average classification success of 66% was achieved.

show abstract

Human-Like Rule Learning from Images Using One-Shot Hypothesis Derivation

Cited by 6 publications

References 23 publications

Towards One-Shot Learning for Text Classification using Inductive Logic Programming

Towards One-Shot Learning for Text Classification using Inductive Logic Programming

An Algebraic Approach to Learning and Grounding

Roof type classification with innovative machine learning approaches

Contact Info

Product

Resources

About