A Framework for Learning Invariant Physical Relations in Multimodal Sensory Processing
This work provides a framework for building consistent representations in engineered systems, which could benefit robotics or AI applications requiring robust sensory processing, though it appears incremental in its approach.
The authors tackled the problem of learning invariant physical relations from multimodal sensory data without prior knowledge of sensor interactions, and demonstrated that their unsupervised neural network can learn non-linear pairwise relations among sensory streams such as light intensity, spatial gradient, and optical flow from RGB camera frames.
Perceptual learning enables humans to recognize and represent stimuli invariant to various transformations and build a consistent representation of the self and physical world. Such representations preserve the invariant physical relations among the multiple perceived sensory cues. This work is an attempt to exploit these principles in an engineered system. We design a novel neural network architecture capable of learning, in an unsupervised manner, relations among multiple sensory cues. The system combines computational principles, such as competition, cooperation, and correlation, in a neurally plausible computational substrate. It achieves that through a parallel and distributed processing architecture in which the relations among the multiple sensory quantities are extracted from time-sequenced data. We describe the core system functionality when learning arbitrary non-linear relations in low-dimensional sensory data. Here, an initial benefit rises from the fact that such a network can be engineered in a relatively straightforward way without prior information about the sensors and their interactions. Moreover, alleviating the need for tedious modelling and parametrization, the network converges to a consistent description of any arbitrary high-dimensional multisensory setup. We demonstrate this through a real-world learning problem, where, from standard RGB camera frames, the network learns the relations between physical quantities such as light intensity, spatial gradient, and optical flow, describing a visual scene. Overall, the benefits of such a framework lie in the capability to learn non-linear pairwise relations among sensory streams in an architecture that is stable under noise and missing sensor input.