NN AND ML——MLP
来源:互联网 发布:nginx配置域名 编辑:程序博客网 时间:2024/06/05 11:22
ADALINE Adaptive Linear classification machine 学习机
MLP:
1. Introduction
- chap4.2 through chap4.7 discuss BP algorithm
- chap4.2 the derivation of the BP algorithm and credit-assignment.
- chap4.3 two kinds of methods of learning: Batch and on-line.
- chap4.4 the derivation of BP algorithm
- chap4.5 solve the XOP problem by BP algorithm.
- chap 4.6 heuristics and practical guidelines for improving BP algorithm performance.
- chap4.7 experiment on the multi-layer perceptron trained with BP algorithm
- chap4.8 through 4.10 include:
- chap4.8 the error surface(误差曲面)
- chap4.9 computational issues relating to the Hessian of the error surface(误差曲面的Hession 矩阵的计算问题).
- chap4.10 How to fulfill optimal annealing and how to make the learning-rate parameter adaptive.(如何实现最优退火以及如何使得学习率参数自适应)
- chap4.11-4.14 include: various matters relating to the performance of a MLP with BP.
- chap 4.11 the issue of generalization(泛化问题)——the essence of learning.
- chap 4.12 the approximation of continuous function by mean of MLP(通过多层感知实现连续函数的逼近问题)
- chap 4.13 Cross Validation(交叉验证)
- chap 4.14 The issue of complexity regularization and network-pruning techniques.
- chap 4.15 The summarizes the advantages and limitations of lack-propagation learning. (反向传播学习的优点和局限性)
- chap 4.16 Viewing supervised learning as an optimization problem.(从不同角度将监督学习看作最优化问题进行讨论)
- chap 4.17 Convolutional Mutilayer Perceptron(cmp) (在解困难识别模式时得到成功的应用)
- chap 4.18 Nonlinear filtering
- chap 4.19 Small-scale versus large-scale learning problem
- chap 4.20 Conclusion
0 0