Representation Benefits of Deep Feedforward Networks
نویسنده
چکیده
This note provides a family of classification problems, indexed by a positive integer k, where all shallow networks with fewer than exponentially (in k) many nodes exhibit error at least 1/6, whereas a deep network with 2 nodes in each of 2k layers achieves zero error, as does a recurrent network with 3 distinct nodes iterated k times. The proof is elementary, and the networks are standard feedforward networks with ReLU (Rectified Linear Unit) nonlinearities.
منابع مشابه
Learning Semantic Prediction using Pretrained Deep Feedforward Networks
The ability to predict future environment states is crucial for anticipative behavior of autonomous agents. Deep learning based methods have proven to solve key perception challenges but currently mainly operate in a non-predictive fashion. We bridge this gap by proposing an approach to transform trained feed-forward networks into predictive ones via a combination of a recurrent predictive modu...
متن کاملRepresentation Results & Algorithms for Deep Feedforward Networks
Despite the fact that parameter optimization for deep feedforward neural networks is highly non-convex, generic gradient methods remain the dominant approach in practice. In part, this is because our understanding of the functions represented by such networks (as compared with simpler flat networks) is still quite limited. This note presents a new representation result for deep neural networks,...
متن کاملDetecting Overlapping Communities in Social Networks using Deep Learning
In network analysis, a community is typically considered of as a group of nodes with a great density of edges among themselves and a low density of edges relative to other network parts. Detecting a community structure is important in any network analysis task, especially for revealing patterns between specified nodes. There is a variety of approaches presented in the literature for overlapping...
متن کاملA unified deep artificial neural network approach to partial differential equations in complex geometries
We use deep feedforward artificial neural networks to approximate solutions of partial differential equations of advection and diffusion type in complex geometries. We derive analytical expressions of the gradients of the cost function with respect to the network parameters, as well as the gradient of the network itself with respect to the input, for arbitrarily deep networks. The method is bas...
متن کاملBiologically Inspired Feedforward Supervised Learning for Deep Self-Organizing Map Networks
In this study, we propose a novel deep neural network and its supervised learning method that uses a feedforward supervisory signal. The method is inspired by the human visual system and performs human-like association-based learning without any backward error propagation. The feedforward supervisory signal that produces the correct result is preceded by the target signal and associates its con...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1509.08101 شماره
صفحات -
تاریخ انتشار 2015