arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.02248cs.LG
收藏

反向传播神经树

Backpropagation Neural Tree

University of Reading(雷丁大学);University of Cambridge(剑桥大学);University of Catania(卡塔尼亚大学)

Varun Ojha, Giuseppe Nicosia

AI总结:

提出 Backpropagation Neural Tree (BNeuralT) 算法,一种模拟生物树突非线性的单神经元神经树模型,通过深度优先搜索的两阶段训练生成高性能且简约的模型,在分类、回归和模式识别任务中平衡复杂度与描述能力。

摘要:

我们提出了一种名为 Backpropagation Neural Tree (BNeuralT) 的新颖算法,它是一个随机计算树突树。BNeuralT 通过其叶子节点接收随机重复输入,并通过其内部连接施加树突非线性,就像生物树突树所做的那样。考虑到类似树突树的合理生物学特性,BNeuralT 是一个单神经元神经树模型,其内部子树类似于树突非线性。BNeuralT 算法生成一个临时神经树,使用随机梯度下降优化器进行训练,如 gradient descent (GD)、momentum GD、Nesterov accelerated GD、Adagrad、RMSprop 或 Adam。BNeuralT 训练分为两个阶段,每个阶段均以深度优先搜索方式计算:前向传播以后序遍历计算神经树的输出,而反向传播期间的误差反向传播则以先序遍历递归执行。BNeuralT 模型可被视为神经网络 (NN) 的最小子集,这意味着它是一个“精简的”NN,其复杂度低于普通 NN。我们的算法在各种机器学习问题上产生了高性能且简约的模型,在分类、回归和模式识别中平衡了复杂度与描述能力。

英文摘要:

We propose a novel algorithm called Backpropagation Neural Tree (BNeuralT), which is a stochastic computational dendritic tree. BNeuralT takes random repeated inputs through its leaves and imposes dendritic nonlinearities through its internal connections like a biological dendritic tree would do. Considering the dendritic-tree like plausible biological properties, BNeuralT is a single neuron neural tree model with its internal sub-trees resembling dendritic nonlinearities. BNeuralT algorithm produces an ad hoc neural tree which is trained using a stochastic gradient descent optimizer like gradient descent (GD), momentum GD, Nesterov accelerated GD, Adagrad, RMSprop, or Adam. BNeuralT training has two phases, each computed in a depth-first search manner: the forward pass computes neural tree's output in a post-order traversal, while the error backpropagation during the backward pass is performed recursively in a pre-order traversal. A BNeuralT model can be considered a minimal subset of a neural network (NN), meaning it is a "thinned" NN whose complexity is lower than an ordinary NN. Our algorithm produces high-performing and parsimonious models balancing the complexity with descriptive ability on a wide variety of machine learning problems: classification, regression, and pattern recognition.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑