We begin with the hypothesis that a model-free agent whose representations are predictive of properties of future states (beyond expected rewards) will be more capable of solving and adapting to new RL problems.

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

EV tax credits are dead in the US. Federal EV tax credits in the US officially came to an end yesterday. Those credits, expanded and extended in the 2022 Inflation Reduction Act, gave drivers up to $7,500 toward the purchase of a new electric vehicle. They've been a major force in cutting the up-front costs of EVs, pushing more people toward purchasing them and giving automakers confidence that demand would be strong. The tax credits' demise comes at a time when battery-electric vehicles still make up a small percentage of new vehicle sales in the country. This article is from The Spark, MIT Technology Review's weekly climate newsletter.

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

Multidimensional recurrent neural networks (MDRNNs) have shown a remarkable performance in the area of speech and handwriting recognition. The performance of an MDRNN is improved by further increasing its depth, and the difficulty of learning the deeper network is overcome by using Hessian-free (HF) optimization. Given that connectionist temporal classification (CTC) is utilized as an objective of learning an MDRNN for sequence labeling, the non-convexity of CTC poses a problem when applying HF to the network. As a solution, a convex approximation of CTC is formulated and its relationship with the EM algorithm and the Fisher information matrix is discussed. An MDRNN up to a depth of 15 layers is successfully trained using HF, resulting in an improved performance for sequence labeling.

Many recent breakthroughs in deep learning were achieved by training increasingly larger models on massive datasets. However, training such models can be prohibitively expensive.

Our experimental contributions are multifold.

Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of neural networks trained in a purely discriminative fashion. Within the model, textures are represented by the correlations between feature maps in several layers of the network. We show that across layers the texture representations increasingly capture the statistical properties of natural images while making object information more and more explicit. The model provides a new tool to generate stimuli for neuroscience and might offer insights into the deep representations learned by convolutional neural networks.