منابع مشابه
Introspective Forecasting
Science ultimately seeks to reliably predict aspects of the future; but, how is this even possible in light of the logical paradox that making a prediction may cause the world to evolve in a manner that defeats it? We show how learning can naturally resolve this conundrum. The problem is studied within a causal or temporal version of the Probably Approximately Correct semantics, extended so tha...
متن کاملIntrospective Forgetting
We model the forgetting of propositional variables in a modal logical context where agents become ignorant and are aware of each others’ or their own resulting ignorance. The resulting logic is sound and complete. It can be compared to variable-forgetting as abstraction from information, wherein agents become unaware of certain variables: by employing elementary results for bisimulation, it fol...
متن کاملMichel Deza , Michel Petitjean , Krassimir Markov
We study differential-geometrical structure of an information manifold equipped with a divergence function.A divergence function generates a Riemannian metric and furthermore it provides a symmetric third-order tensor,when the divergence is asymmetric. This induces a pair of affine connections dually coupled to each other withrespect to the Riemannian metric. This is the arising eme...
متن کاملMichel Labouesse
Michel Labouesse grew up near Paris. He studied maths and physics for a degree in engineering, but subsequently embraced a career in biology. He learned genetics during his PhD with Piotr Slonimski in Gif/Yvette, where he analysed how the nuclear genome controls expression of mitochondrial genes in yeast. He then went on to learn developmental biology of the nematode Caenorhabditis elegans as a...
متن کاملWasserstein Introspective Neural Networks
We present Wasserstein introspective neural networks (WINN) that are both a generator and a discriminator within a single model. WINN provides a significant improvement over the recent introspective neural networks (INN) method by enhancing INN’s generative modeling capability. WINN has three interesting properties: (1) A mathematical connection between the formulation of the INN algorithm and ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Critique d’art
سال: 2018
ISSN: 1246-8258,2265-9404
DOI: 10.4000/critiquedart.27475