Learning to solve arithmetic problems with a virtual abacus
- URL: http://arxiv.org/abs/2301.06870v1
- Date: Tue, 17 Jan 2023 13:25:52 GMT
- Title: Learning to solve arithmetic problems with a virtual abacus
- Authors: Flavio Petruzzellis, Ling Xuan Chen, Alberto Testolin
- Abstract summary: We introduce a deep reinforcement learning framework that allows to simulate how cognitive agents could learn to solve arithmetic problems.
The proposed model successfully learns to perform multi-digit additions and subtractions, achieving an error rate below 1%.
We analyze the most common error patterns to better understand the limitations and biases resulting from our design choices.
- Score: 0.35911228556176483
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Acquiring mathematical skills is considered a key challenge for modern
Artificial Intelligence systems. Inspired by the way humans discover numerical
knowledge, here we introduce a deep reinforcement learning framework that
allows to simulate how cognitive agents could gradually learn to solve
arithmetic problems by interacting with a virtual abacus. The proposed model
successfully learn to perform multi-digit additions and subtractions, achieving
an error rate below 1% even when operands are much longer than those observed
during training. We also compare the performance of learning agents receiving a
different amount of explicit supervision, and we analyze the most common error
patterns to better understand the limitations and biases resulting from our
design choices.
Related papers
- Offline Imitation Learning Through Graph Search and Retrieval [57.57306578140857]
Imitation learning is a powerful machine learning algorithm for a robot to acquire manipulation skills.
We propose GSR, a simple yet effective algorithm that learns from suboptimal demonstrations through Graph Search and Retrieval.
GSR can achieve a 10% to 30% higher success rate and over 30% higher proficiency compared to baselines.
arXiv Detail & Related papers (2024-07-22T06:12:21Z) - Improving deep learning with prior knowledge and cognitive models: A
survey on enhancing explainability, adversarial robustness and zero-shot
learning [0.0]
We review current and emerging knowledge-informed and brain-inspired cognitive systems for realizing adversarial defenses.
Brain-inspired cognition methods use computational models that mimic the human mind to enhance intelligent behavior in artificial agents and autonomous robots.
arXiv Detail & Related papers (2024-03-11T18:11:00Z) - The Clock and the Pizza: Two Stories in Mechanistic Explanation of
Neural Networks [59.26515696183751]
We show that algorithm discovery in neural networks is sometimes more complex.
We show that even simple learning problems can admit a surprising diversity of solutions.
arXiv Detail & Related papers (2023-06-30T17:59:13Z) - Can neural networks do arithmetic? A survey on the elementary numerical
skills of state-of-the-art deep learning models [0.424243593213882]
It is unclear whether deep learning models possess an elementary understanding of quantities and symbolic numbers.
We critically examine the recent literature, concluding that even state-of-the-art architectures often fall short when probed with relatively simple tasks designed to test basic numerical and arithmetic knowledge.
arXiv Detail & Related papers (2023-03-14T09:30:52Z) - Anti-Retroactive Interference for Lifelong Learning [65.50683752919089]
We design a paradigm for lifelong learning based on meta-learning and associative mechanism of the brain.
It tackles the problem from two aspects: extracting knowledge and memorizing knowledge.
It is theoretically analyzed that the proposed learning paradigm can make the models of different tasks converge to the same optimum.
arXiv Detail & Related papers (2022-08-27T09:27:36Z) - Transformers discover an elementary calculation system exploiting local
attention and grid-like problem representation [0.424243593213882]
We show that universal transformers equipped with local attention and adaptive halting mechanisms can learn to exploit an external, grid-like memory to carry out multi-digit addition.
The proposed model achieves remarkable accuracy even when tested with problems requiring extrapolation outside the training distribution.
arXiv Detail & Related papers (2022-07-06T09:29:56Z) - Systematic human learning and generalization from a brief tutorial with
explanatory feedback [3.7826494079172557]
We investigate human adults' ability to learn an abstract reasoning task based on Sudoku.
We find that participants who master the task do so within a small number of trials and generalize well to puzzles outside of the training range.
We also find that most of those who master the task can describe a valid solution strategy, and such participants perform better on transfer puzzles than those whose strategy descriptions are vague or incomplete.
arXiv Detail & Related papers (2021-07-10T00:14:41Z) - Reset-Free Reinforcement Learning via Multi-Task Learning: Learning
Dexterous Manipulation Behaviors without Human Intervention [67.1936055742498]
We show that multi-task learning can effectively scale reset-free learning schemes to much more complex problems.
This work shows the ability to learn dexterous manipulation behaviors in the real world with RL without any human intervention.
arXiv Detail & Related papers (2021-04-22T17:38:27Z) - Recognizing and Verifying Mathematical Equations using Multiplicative
Differential Neural Units [86.9207811656179]
We show that memory-augmented neural networks (NNs) can achieve higher-order, memory-augmented extrapolation, stable performance, and faster convergence.
Our models achieve a 1.53% average improvement over current state-of-the-art methods in equation verification and achieve a 2.22% Top-1 average accuracy and 2.96% Top-5 average accuracy for equation completion.
arXiv Detail & Related papers (2021-04-07T03:50:11Z) - Machine Number Sense: A Dataset of Visual Arithmetic Problems for
Abstract and Relational Reasoning [95.18337034090648]
We propose a dataset, Machine Number Sense (MNS), consisting of visual arithmetic problems automatically generated using a grammar model--And-Or Graph (AOG)
These visual arithmetic problems are in the form of geometric figures.
We benchmark the MNS dataset using four predominant neural network models as baselines in this visual reasoning task.
arXiv Detail & Related papers (2020-04-25T17:14:58Z)
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.