How are neural networks related to Fourier transforms
2017-07-14 10:53
363 查看
本篇是转载的文章,来源链接如下:
https://www.quora.com/How-are-neural-networks-related-to-Fourier-transforms
核心是解答一个常见的、但是又不容易搞清楚的问题:CNN为基础的深度学习跟常规的数学运算,例如FFT是什么关系?
下文的回答主要包含两个部分,即深度学习与FFT的相同和不同之处。
Taylor series and Fourier Series are function approximation techniques.
The neural network is itself is a function approximation( Universal Function approximation).
Image Source: Neural Networks by Raul Rojas.
This image shows how to use Taylor series and Fourier series as Neural Network.
But the difference between the (Taylor series or Fourier series )and Artificial Neural networks is ..
Artificial Neural Networks are used to approximate an unknown function and only function value at some points are given. Task is to learn the function ( or approximate) by using these given points and generalize as best as we can by a learning technique. Parameters
are learned using an iterative technique like gradient descent.
The parameters in Taylor series a1,a2,a3,... are found by finding the nth order derivatives of the function at particular points. In the same way Fourier parameters can also be found by evaluating the given function. Parameters are directly computed using formula
applied to actual function.
https://www.quora.com/How-are-neural-networks-related-to-Fourier-transforms
核心是解答一个常见的、但是又不容易搞清楚的问题:CNN为基础的深度学习跟常规的数学运算,例如FFT是什么关系?
下文的回答主要包含两个部分,即深度学习与FFT的相同和不同之处。
Taylor series and Fourier Series are function approximation techniques.
The neural network is itself is a function approximation( Universal Function approximation).
Image Source: Neural Networks by Raul Rojas.
This image shows how to use Taylor series and Fourier series as Neural Network.
But the difference between the (Taylor series or Fourier series )and Artificial Neural networks is ..
Artificial Neural Networks are used to approximate an unknown function and only function value at some points are given. Task is to learn the function ( or approximate) by using these given points and generalize as best as we can by a learning technique. Parameters
are learned using an iterative technique like gradient descent.
The parameters in Taylor series a1,a2,a3,... are found by finding the nth order derivatives of the function at particular points. In the same way Fourier parameters can also be found by evaluating the given function. Parameters are directly computed using formula
applied to actual function.
相关文章推荐
- How to improve neural networks learning
- How to design DL model(1):Efficient Convolutional Neural Networks for Mobile Vision Applications
- How to calculate the number of parameters of Convolutional Neural Networks(CNNs) correctly?
- CHAPTER 5 Why are deep neural networks hard to train?
- 为什么深度神经网络难以训练Why are deep neural networks hard to train?
- Learning How To Code Neural Networks
- (zhuan) Attention in Neural Networks and How to Use It
- 读书笔记 How transferable are features in deep neural networks?
- What is PTT? What is PoC? How are these related to SIP?
- How to Create Transportable Tablespaces Where the Source and Destination are ASM-Based
- How to Find the Self Service Related File Location and Versions
- Sequence to Sequence Learning with Neural Networks
- How are TCP/IP and HTTP related?
- 《How to Use the TimeDistributed Layer for Long Short-Term Memory Networks in Python》学习笔记
- (翻译)Sequence to Sequence Learning with Neural Networks
- Introduction to debugging neural networks
- Learning to Compare Image Patches via Convolutional Neural Networks
- How are Receiving Transaction Tied to Inventory Transactions?
- 【论文笔记】Sequence to sequence Learning with Neural Networks
- 论文学习:Learning to Compare Image Patches via Convolutional Neural Networks