Neural Program Lattices
نویسندگان
چکیده
We propose the Neural Program Lattice (NPL), a neural network that learns to perform complex tasks by composing low-level programs to express high-level programs. Our starting point is the recent work on Neural Programmer-Interpreters (NPI), which can only learn from strong supervision that contains the whole hierarchy of low-level and high-level programs. NPLs remove this limitation by providing the ability to learn from weak supervision consisting only of sequences of low-level operations. We demonstrate the capability of NPL to learn to perform long-hand addition and arrange blocks in a grid-world environment. Experiments show that it performs on par with NPI while using weak supervision in place of most of the strong supervision, thus indicating its ability to infer the high-level program structure from examples containing only the low-level operations.
منابع مشابه
‘Neural Net Simulation on Transputers
2 Neural Nets, Statistical Physics and Optimization It has recently been shown that neural net models can be based upon the principles of statistical physics, In particular the spin sociative memories and optimization networks. The simulation of such neural networks promises to provide valuable insights into human and machine vision. However, for a large amay, the calculations involved become p...
متن کاملRegularity in residuated lattices
In this paper, we study residuated lattices in order to give new characterizations for dense, regular and Boolean elements in residuated lattices and investigate special residuated lattices in order to obtain new characterizations for the directly indecomposable subvariety of Stonean residuated lattices. Free algebra in varieties of Stonean residuated lattices is constructed. We introduce in re...
متن کاملAn Application of Formal Concept Analysis to Neural Decoding
This paper proposes a novel application of Formal Concept Analysis (FCA) to neural decoding: the semantic relationships between the neural representations of large sets of stimuli are explored using concept lattices. In particular, the effects of neural code sparsity are modelled using the lattices. An exact Bayesian approach is employed to construct the formal context needed by FCA. This metho...
متن کاملCreating of Conceptual Lattices using Multilayer Perceptron
Creating of concept lattices is unfortunately difficult timeconsuming process. Neural networks can solve this problem, because they are adaptive in nature, due to their use of a training phase for learning the relationships in the input data, and their generalization capabilities provide a means of coping with noisy or incomplete data. In this text there is presented one possible approach to cr...
متن کاملAn equivalence functor between local vector lattices and vector lattices
We call a local vector lattice any vector lattice with a distinguished positive strong unit and having exactly one maximal ideal (its radical). We provide a short study of local vector lattices. In this regards, some characterizations of local vector lattices are given. For instance, we prove that a vector lattice with a distinguished strong unit is local if and only if it is clean with non no-...
متن کامل