Probabilistic Neural Programs
ثبت نشده
چکیده
We present probabilistic neural programs, a framework for program induction that 1 permits flexible specification of both a computational model and inference algo2 rithm while simultaneously enabling the use of deep neural networks. Probabilistic 3 neural programs combine a computation graph for specifying a neural network with 4 an operator for weighted nondeterministic choice. Thus, a program describes both 5 a collection of decisions as well as the neural network architecture used to make 6 each one. We evaluate our approach on a challenging diagram question answering 7 task where probabilistic neural programs correctly execute nearly twice as many 8 programs as a baseline model. 9
منابع مشابه
Probabilistic Neural Programs
We present probabilistic neural programs, a framework for program induction that permits flexible specification of both a computational model and inference algorithm while simultaneously enabling the use of deep neural networks. Probabilistic neural programs combine a computation graph for specifying a neural network with an operator for weighted nondeterministic choice. Thus, a program describ...
متن کاملDesigning of a New Transformer Ground Differential Relay Based on Probabilistic Neural Network
Low- impedance transformer ground differential relay is a part of power transformer protection system that is employed for detecting the internal earth faults. This is a fast and sensitive relay, but during some external faults and inrush current conditions, may be exposed to maloperation due to current transformer (CT) saturation. In this paper, a new intelligent transformer ground differentia...
متن کاملLearning Probabilistic Programs Using Backpropagation
Probabilistic modeling enables combining domain knowledge with learning from data, thereby supporting learning from fewer training instances than purely data-driven methods. However, learning probabilistic models is difficult and has not achieved the level of performance of methods such as deep neural networks on many tasks. In this paper, we attempt to address this issue by presenting a method...
متن کاملUsing probabilistic programs as proposals
Monte Carlo inference has asymptotic guarantees, but can be slow when using generic proposals. Handcrafted proposals that rely on user knowledge about the posterior distribution can be efficient, but are difficult to derive and implement. This paper proposes to let users express their posterior knowledge in the form of proposal programs, which are samplers written in probabilistic programming l...
متن کاملMapping Logical Bayesian Networks to Probabilistic Logic Programs with Distribution Semantics
A significant part of current research on (inductive) logic programming deals with probabilistic logical models. Over the last decade many logics or languages for representing such models have been introduced. There is currently a great need for insight into the relationships between all these languages. One kind of languages are those that extend probabilistic models with elements of logic, su...
متن کامل