An Explicitly Relational Neural Network Architecture

With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data. In order to evaluate and analyse the architecture, we introduce a family of simple visual relational reasoning tasks of varying complexity. We show that the proposed architecture, when pre-trained on a curriculum of such tasks, learns to generate reusable representations that better facilitate subsequent learning on previously unseen tasks when compared to a number of baseline architectures. The workings of a successfully trained model are visualised to shed some light on how the architecture functions.

[1]  Murray Shanahan,et al.  Towards Deep Symbolic Reinforcement Learning , 2016, ArXiv.

[2]  Alex Mott,et al.  Towards Interpretable Reinforcement Learning Using Attention Augmented Agents , 2019, NeurIPS.

[3]  Tim Rocktäschel,et al.  End-to-end Differentiable Proving , 2017, NIPS.

[4]  Razvan Pascanu,et al.  Deep reinforcement learning with relational inductive biases , 2018, ICLR.

[5]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[6]  Brian Cantwell Smith,et al.  The Promise of Artificial Intelligence: Reckoning and Judgment , 2019 .

[7]  John McCarthy,et al.  Generality in artificial intelligence , 1987, Resonance.

[8]  Murray Shanahan,et al.  SCAN: Learning Hierarchical Compositional Visual Concepts , 2017, ICLR.

[9]  Andrew McCallum,et al.  Introduction to Statistical Relational Learning , 2007 .

[10]  Christopher Burgess,et al.  DARLA: Improving Zero-Shot Transfer in Reinforcement Learning , 2017, ICML.

[11]  Gary Marcus,et al.  Deep Learning: A Critical Appraisal , 2018, ArXiv.

[12]  Li Fei-Fei,et al.  CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Joshua B. Tenenbaum,et al.  Building machines that learn and think like people , 2016, Behavioral and Brain Sciences.

[15]  Chong Wang,et al.  Neural Logic Machines , 2019, ICLR.

[16]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[17]  Masataro Asai,et al.  Unsupervised Grounding of Plannable First-Order Logic Representation from Images , 2019, ICAPS.

[18]  Abhinav Gupta,et al.  Non-local Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[19]  Richard Evans,et al.  Learning Explanatory Rules from Noisy Data , 2017, J. Artif. Intell. Res..

[20]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[21]  Ole Winther,et al.  Recurrent Relational Networks , 2017, NeurIPS.

[22]  Yoshua Bengio,et al.  Deep Learning of Representations for Unsupervised and Transfer Learning , 2011, ICML Unsupervised and Transfer Learning.

[23]  Dileep George,et al.  Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics , 2017, ICML.

[24]  Ieee Xplore,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence Information for Authors , 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Jason Weston,et al.  Learning Structured Embeddings of Knowledge Bases , 2011, AAAI.

[26]  Yee Whye Teh,et al.  Progress & Compress: A scalable framework for continual learning , 2018, ICML.

[27]  Murray Shanahan,et al.  Reconciling deep learning with symbolic artificial intelligence: representing objects and relations , 2019, Current Opinion in Behavioral Sciences.

[28]  Razvan Pascanu,et al.  Imagination-Augmented Agents for Deep Reinforcement Learning , 2017, NIPS.

[29]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[30]  Razvan Pascanu,et al.  Relational recurrent neural networks , 2018, NeurIPS.

[31]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[32]  Danqi Chen,et al.  Reasoning With Neural Tensor Networks for Knowledge Base Completion , 2013, NIPS.

[33]  Lukasz Kaiser,et al.  Universal Transformers , 2018, ICLR.

[34]  Razvan Pascanu,et al.  A simple neural network module for relational reasoning , 2017, NIPS.