Inspired by predictive coding - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural networks, PCN includes both feedback connections, which carry top-down predictions, and feedforward connections, which carry bottom-up errors of prediction. Feedback and feedforward connections enable adjacent layers to interact locally and recurrently to refine representations towards minimization of layer-wise prediction errors. When unfolded over time, the recurrent processing gives rise to an increasingly deeper hierarchy of non-linear transformation, allowing a shallow network to dynamically extend itself into an arbitrarily deep network.

A.1 PCNtraining We basically follow the same PCN training method by Wu et al.[1] but replace the AlphaZero algorithm with the Gumbel AlphaZero algorithm [2], where the simulation count is set to 322 in self-play and starts by sampling 16 actions. The architecture of the PCN contains three residual blocks with 256 hidden channels. Atotal of400,000 self-play games are generated for the whole training. During optimization, the learning rate is fixed at 0.02, and the batch size is set to 1,024. A.3 Workerdesign The worker is itself a Killall-Go solver. Thus,tofullyutilize GPU resources, we implement batch GPU inferencing to accelerate PCN evaluations for workers.

Neural Information Processing Systems http://nips.cc/

Throughout our lives, we learn a huge number of associations between concepts: the taste of a particularfood,themeaningofagesture,ortostopwhenweseearedlight.

Inspired by predictive coding - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural networks, PCN includes both feedback connections, which carry top-down predictions, and feedforward connections, which carry bottom-up errors of prediction. Feedback and feedforward connections enable adjacent layers to interact locally and recurrently to refine representations towards minimization of layer-wise prediction errors. When unfolded over time, the recurrent processing gives rise to an increasingly deeper hierarchy of non-linear transformation, allowing a shallow network to dynamically extend itself into an arbitrarily deep network.

Inspired by "predictive coding" - a theory in neuroscience, we develop a bidirectional and dynamic neural network with local recurrent processing, namely

W e propose tokenization of events and present a tokenizer, Spiking Patches, specifically designed for event cameras. Given a stream of asynchronous and spatially sparse events, our goal is to discover an event representation that preserves these properties. Prior works have represented events as frames or as voxels. However, while these representations yield high accuracy, both frames and voxels are synchronous and decrease the spatial sparsity. Spiking Patches gives the means to preserve the unique properties of event cameras and we show in our experiments that this comes without sacrificing accuracy. W e evaluate our tokenizer using a GNN, PCN, and a Transformer on gesture recognition and object detection. T okens from Spiking Patches yield inference times that are up to 3.4x faster than voxel-based tokens and up to 10.4x faster than frames. W e achieve this while matching their accuracy and even surpassing in some cases with absolute improvements up to 3.8 for gesture recognition and up to 1.4 for object detection. Thus, tokenization constitutes a novel direction in event-based vision and marks a step towards methods that preserve the properties of event cameras.

Game solving is a similar, yet more difficult task than mastering a game.