Artificial Neural Networks in Pattern Recognition

Abstract

Bounded rationality investigates utility-optimizing decisionmakers with limited information-processing power. In particular, information theoretic bounded rationality models formalize resource constraints abstractly in terms of relative Shannon information, namely the Kullback-Leibler Divergence between the agents' prior and posterior policy. Between prior and posterior lies an anytime deliberation process that can be instantiated by sample-based evaluations of the utility function through Markov Chain Monte Carlo (MCMC) optimization. The most simple model assumes a fixed prior and can relate abstract informationtheoretic processing costs to the number of sample evaluations. However, more advanced models would also address the question of learning, that is how the prior is adapted over time such that generated prior proposals become more efficient. In this work we investigate generative neural networks as priors that are optimized concurrently with anytime sample-based decision-making processes such as MCMC. We evaluate this approach on toy examples.

HexagDLy—Processing hexagonally sampled data with CNNs in PyTorch

“…This data is often hexagonally sampled, which poses an initial obstacle for the application of CNNs: DLFs cannot process hexagonally sampled data out-of-the-box. Solutions to this problem have been presented in several applicability studies [2,3,4,5,6,7]. Most of these solutions are based on transforming the hexagonally sampled data to an approximate representation on a rectangular grid via pre-processing such as rebinning, interpolation, oversampling and axis-shearing.…”

Reconstruction of stereoscopic CTA events using deep learning with CTLearn

“…Previous works have demonstrated the potential application of these algorithms for IACT event reconstruction [8][9][10][11][12][13]. DCN-based monoscopic telescope performance and the application of DCNs on observational data from the first Large-Sized Telescope (LST-1 prototype) of CTA North is discussed in these proceedings elsewhere [14,15].…”

Reconstruction of IACT events using deep learning techniques with CTLearn

“…The ability of deep learning to assist in the analysis of data from imaging atmospheric Cherenkov telescopes (IACT) was first demonstrated by the detection of muon rings in real data (Feng & Lin 2016) and by the classification of gamma-ray and cosmicray simulated events (Nieto et al 2017). Subsequent studies proved its capability to reconstruct the energy and arrival direction of simulated gamma-ray events (Mangano et al 2018;Jacquemont et al 2020) and to improve IACT sensitivity on real data (Shilon et al 2019). CTLearn 1 (Nieto et al 2019a;) is a high-level, open-source Python package providing a backend for training deep learning models for IACT event reconstruction using TensorFlow.…”