Object-Oriented Learning (OOL): Perception, Representation, and Reasoning
Friday July 17, 2020, Virtual Workshop
Objects, and the interactions between them, are the foundations on which our understanding of the world is built . Similarly, abstractions centered around the perception and representation of objects play a key role in building human-like AI, supporting high-level cognitive abilities like causal reasoning, object-centric exploration, and problem solving [2,4,5,6]. Indeed, prior works have shown how relational reasoning and control problems can greatly benefit from having object descriptions [2,7]. Yet, many of the current methods in machine learning focus on a less structured approach in which objects are only implicitly represented , posing a challenge for interpretability and the reuse of knowledge across tasks. Motivated by the above observations, there has been a recent effort to reinterpret various learning problems from the perspective of object-oriented representations [2,4,5,6].
In this workshop, we will showcase a variety of approaches in object-oriented learning, with three particular emphases. Our first interest is in learning object representations in an unsupervised manner. Although computer vision has made an enormous amount of progress in learning about objects via supervised methods, we believe that learning about objects with little to no supervision is preferable: it minimizes labeling costs, and also supports adaptive representations that can be changed depending on the particular situation and goal. The second primary interest of this workshop is to explore how object-oriented representations can be leveraged for downstream tasks such as reinforcement learning and causal reasoning. Lastly, given the central importance of objects in human cognition, we will highlight interdisciplinary perspectives from cognitive science and neuroscience on how people perceive and understand objects.
- Spelke, E. S., & Kinzler, K. D. (2007). Core knowledge. Developmental science, 10(1), 89-96.
- Bapst, V., Sanchez-Gonzalez, A., Doersch, C., Stachenfeld, K. L., Kohli, P., Battaglia, P. W., & Hamrick, J. B. (2019). Structured agents for physical construction. ICML 2019.
- Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., ... & Petersen, S. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529-533.
- Kosiorek, A., Kim, H., Teh, Y.W. and Posner, I., (2018). Sequential attend, infer, repeat: Generative modelling of moving objects. In Advances in Neural Information Processing Systems 2018.
- Lin, Z., Wu, Y.F., Peri, S.V., Sun, W., Singh, G., Deng, F., Jiang, J. and Ahn, S., (2020). SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition. ICLR 2020.
- van Steenkiste, S., Chang, M., Greff, K., & Schmidhuber, J. (2018). Relational neural expectation maximization: Unsupervised discovery of objects and their interactions. ICLR 2018.
- Diuk, C., Cohen, A., & Littman, M. L. (2008, July). An object-oriented representation for efficient reinforcement learning. ICML 2008.