convolutional-neural-network

This paper introduces a learnable channel-class assignment mechanism for forward-only convolutional neural networks, combined with entropy and orthogonality regularization and a loss-aware layer contribution strategy. The method achieves state-of-the-art performance among forward-forward algorithms on CIFAR-10, CIFAR-100, and Tiny-ImageNet, significantly narrowing the gap with backpropagation.

OpenAI trained 9 agents on the CoinRun environment with varying numbers of training levels to quantify generalization in reinforcement learning, finding substantial overfitting even with 16,000 training levels and that IMPALA-CNN architectures generalize significantly better than Nature-CNN baselines.