[Links of the Day] 23/04/2020 : Machine Learning technical debt, Python and Bayesian Deep Learning perspective of generalization

• Bayesian Deep Learning and a Probabilistic Perspective of Generalization : the authors propose and demonstrate that ensembles provide an effective mechanism for approximate Bayesian marginalization, and propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction, without significant overhead.
• The High Interest Credit Card of Technical Debt for Machine learning : machine learning solutions are not simple, and technical debt is expensive to pay back.
• Machine Learning in Python : Main developments and technology trends in data science, machine learning, and artificial intelligence centred around python.