Growing axons: greedy learning of neural networks with application to function approximation
We propose a new method for learning deep neural network models that is based on a greedy learning approach: we add one basis function at a time, and a new basis function is generated as a non-linear activation function applied to a linear combination of the previous basis functions. Such a method (growing deep neural network by one neuron at a time) allows us to compute much more accurate approximants for several model problems in function approximation.
Code (1)
Similar Papers 제목 키워드 기반
Non-submodular Function Maximization subject to a Matroid Constraint, with Applications
The standard greedy algorithm has been recently shown to enjoy approximation guarantees for constrained non-submodular nondecreasing set function maximization. While these recent results allow to better characterize the …
Point ProcessesTracking of plus-ends reveals microtubule functional diversity in different cell types
Many cellular processes are tightly connected to the dynamics of microtubules (MTs). While in neuronal axons MTs mainly regulate intracellular trafficking, they participate in cytoskeleton reorganization in many other eu…
DiversityGreed is Good: Near-Optimal Submodular Maximization via Greedy Optimization
It is known that greedy methods perform well for maximizing monotone submodular functions. At the same time, such methods perform poorly in the face of non-monotonicity. In this paper, we show - arguably, surprisingly - …
Movie RecommendationOrthogonal greedy algorithm for linear operator learning with shallow neural network
Greedy algorithms, particularly the orthogonal greedy algorithm (OGA), have proven effective in training shallow neural networks for fitting functions and solving partial differential equations (PDEs). In this paper, we …
Operator learningRobust Subset Selection by Greedy and Evolutionary Pareto Optimization
Subset selection, which aims to select a subset from a ground set to maximize some objective function, arises in various applications such as influence maximization and sensor placement. In real-world scenarios, however,…