Symmetric discrete universal neural networks
نویسندگان
چکیده
منابع مشابه
Symmetric Discrete Universal Neural Networks
Given the class of symmetric discrete weight neural networks with finite state set (0, l}, we prove that there exist iteration modes under these networks which allow to simulate in linear space arbitrary neural networks (non-necessarily symmetric). As a particular result we prove that an arbitrary symmetric neural network can be simulated by a symmetric one iterated sequentially, with some nega...
متن کاملNeural Universal Discrete Denoiser
We present a new framework of applying deep neural networks (DNN) to devise a universal discrete denoiser. Unlike other approaches that utilize supervised learning for denoising, we do not require any additional training data. In such setting, while the ground-truth label, i.e., the clean data, is not available, we devise “pseudolabels” and a novel objective function such that DNN can be traine...
متن کاملHybrid discrete-time neural networks.
Hybrid dynamical systems combine evolution equations with state transitions. When the evolution equations are discrete-time (also called map-based), the result is a hybrid discrete-time system. A class of biological neural network models that has recently received some attention falls within this category: map-based neuron models connected by means of fast threshold modulation (FTM). FTM is a c...
متن کاملNeural Networks for Discrete Tomography
Discrete tomography deals with the reconstruction of binary images from their projections in a small number of directions. In this paper we consider possible neural network approaches to this tomographic reconstruction problem. In particular we are interested in methods that can compute reconstructions in real-time and make efficient use of prior knowledge about the images, even when this knowl...
متن کاملAnalog versus discrete neural networks
We show that neural networks with three-times continuously differentiable activation functions are capable of computing a certain family of n-bit boolean functions with two gates, whereas networks composed of binary threshold functions require at least omega(log n) gates. Thus, for a large class of activation functions, analog neural networks can be more powerful than discrete neural networks, ...
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: Theoretical Computer Science
سال: 1996
ISSN: 0304-3975
DOI: 10.1016/s0304-3975(96)00085-0