Solving Raven's Progressive Matrices with Neural Networks
- URL: http://arxiv.org/abs/2002.01646v2
- Date: Thu, 6 Feb 2020 13:58:52 GMT
- Title: Solving Raven's Progressive Matrices with Neural Networks
- Authors: Tao Zhuo and Mohan Kankanhalli
- Abstract summary: Raven's Progressive Matrices (RPM) have been widely used for Intelligence Quotient (IQ) test of humans.
In this paper, we aim to solve RPM with neural networks in both supervised and unsupervised manners.
- Score: 10.675709291797535
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Raven's Progressive Matrices (RPM) have been widely used for Intelligence
Quotient (IQ) test of humans. In this paper, we aim to solve RPM with neural
networks in both supervised and unsupervised manners. First, we investigate
strategies to reduce over-fitting in supervised learning. We suggest the use of
a neural network with deep layers and pre-training on large-scale datasets to
improve model generalization. Experiments on the RAVEN dataset show that the
overall accuracy of our supervised approach surpasses human-level performance.
Second, as an intelligent agent requires to automatically learn new skills to
solve new problems, we propose the first unsupervised method, Multilabel
Classification with Pseudo Target (MCPT), for RPM problems. Based on the design
of the pseudo target, MCPT converts the unsupervised learning problem to a
supervised task. Experiments show that MCPT doubles the testing accuracy of
random guessing e.g. 28.50% vs. 12.5%. Finally, we discuss the problem of
solving RPM with unsupervised and explainable strategies in the future.
Related papers
- ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks [0.0]
We present ExpTest, a sophisticated method for initial learning rate searching and subsequent learning rate tuning.
We mathematically justify ExpTest and provide empirical support.
arXiv Detail & Related papers (2024-11-25T22:58:22Z) - Guiding Through Complexity: What Makes Good Supervision for Hard Reasoning Tasks? [74.88417042125985]
We investigate various data-driven strategies that offer supervision data at different quality levels upon tasks of varying complexity.
We find that even when the outcome error rate for hard task supervision is high, training on such data can outperform perfectly correct supervision on easier subtasks.
Our results also reveal that supplementing hard task supervision with the corresponding subtask supervision can yield notable performance improvements.
arXiv Detail & Related papers (2024-10-27T17:55:27Z) - A Study of Forward-Forward Algorithm for Self-Supervised Learning [65.268245109828]
We study the performance of forward-forward vs. backpropagation for self-supervised representation learning.
Our main finding is that while the forward-forward algorithm performs comparably to backpropagation during (self-supervised) training, the transfer performance is significantly lagging behind in all the studied settings.
arXiv Detail & Related papers (2023-09-21T10:14:53Z) - Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks [69.38572074372392]
We present the first results proving that feature learning occurs during training with a nonlinear model on multiple tasks.
Our key insight is that multi-task pretraining induces a pseudo-contrastive loss that favors representations that align points that typically have the same label across tasks.
arXiv Detail & Related papers (2023-07-13T16:39:08Z) - Are Deep Neural Networks SMARTer than Second Graders? [85.60342335636341]
We evaluate the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed for children in the 6--8 age group.
Our dataset consists of 101 unique puzzles; each puzzle comprises a picture question, and their solution needs a mix of several elementary skills, including arithmetic, algebra, and spatial reasoning.
Experiments reveal that while powerful deep models offer reasonable performances on puzzles in a supervised setting, they are not better than random accuracy when analyzed for generalization.
arXiv Detail & Related papers (2022-12-20T04:33:32Z) - Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment.
We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent.
We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
arXiv Detail & Related papers (2022-09-24T14:22:29Z) - Effective Abstract Reasoning with Dual-Contrast Network [10.675709291797535]
We aim to solve Raven's Progressive Matrices ( RPM) puzzles with neural networks.
We design a simple yet effective Dual-Contrast Network (DCNet) to exploit the inherent structure of RPM puzzles.
Experimental results on the RAVEN and PGM datasets show that DCNet outperforms the state-of-the-art methods by a large margin of 5.77%.
arXiv Detail & Related papers (2022-05-27T02:26:52Z) - Unsupervised Abstract Reasoning for Raven's Problem Matrices [9.278113063631643]
Raven's Progressive Matrices ( RPM) is highly correlated with human intelligence.
We propose the first unsupervised learning method for solving RPM problems.
Our method even outperforms some of the supervised approaches.
arXiv Detail & Related papers (2021-09-21T07:44:58Z) - Pointer Value Retrieval: A new benchmark for understanding the limits of
neural network generalization [40.21297628440919]
We introduce a novel benchmark, Pointer Value Retrieval (PVR) tasks, that explore the limits of neural network generalization.
PVR tasks can consist of visual as well as symbolic inputs, each with varying levels of difficulty.
We demonstrate that this task structure provides a rich testbed for understanding generalization.
arXiv Detail & Related papers (2021-07-27T03:50:31Z) - Stratified Rule-Aware Network for Abstract Visual Reasoning [46.015682319351676]
Raven's Progressive Matrices (RPM) test is typically used to examine the capability of abstract reasoning.
Recent studies, taking advantage of Convolutional Neural Networks (CNNs), have achieved encouraging progress to accomplish the RPM test.
We propose a Stratified Rule-Aware Network (SRAN) to generate the rule embeddings for two input sequences.
arXiv Detail & Related papers (2020-02-17T08:44:05Z)
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.