Why do sigmoid functions work in Neural Nets?

AI Thread Summary
The discussion centers on the workings of Backpropagation (BP) in neural networks, particularly the mathematical justification for using sigmoid functions. The user seeks to understand why the BP algorithm is effective and how sigmoid functions enable neural networks to approximate various data distributions. The inquiry highlights a gap in available resources that explain the theoretical underpinnings of these concepts, emphasizing the need for deeper mathematical insights into the behavior of neural networks during training.
apj_anshul
Messages
5
Reaction score
0
Hi,

I have just started programming for Neural networks. I am currently working on understanding how a Backpropogation (BP) neural net works. While the algorithm for training in BP nets is quite straightforward, I was unable to find any text on why the algorithm works. More specifically, I am looking for some mathematical reasoning to justify using sigmoid functions in neural nets, and what makes them mimic almost any data distribution thrown at them.

Thanks!
 
Technology news on Phys.org
Thread 'Is this public key encryption?'

Thread 'Is this public key encryption?'

I've tried to intuit public key encryption but never quite managed. But this seems to wrap it up in a bow. This seems to be a very elegant way of transmitting a message publicly that only the sender and receiver can decipher. Is this how PKE works? No, it cant be. In the above case, the requester knows the target's "secret" key - because they have his ID, and therefore knows his birthdate.
View full post »

Thread 'Who is responsible for the software when AI takes over programming?'

I tried a web search "the loss of programming ", and found an article saying that all aspects of writing, developing, and testing software programs will one day all be handled through artificial intelligence. One must wonder then, who is responsible. WHO is responsible for any problems, bugs, deficiencies, or whatever malfunctions which the programs make their users endure? Things may work wrong however the "wrong" happens. AI needs to fix the problems for the users. Any way to...
View full post »

Similar threads

Why is my multilayered, feedforward neural network not working?
2
Replies
50
Views
4K
Normalization condition with a neural network
Replies
3
Views
1K
Neural Nets in AI: What's the Intelligent Part?
Replies
19
Views
3K
Python Building a homemade Long Short Term Memory with FSMs
Replies
2
Views
2K
Thoughts on neural networks "discovering" physical concepts
Replies
1
Views
2K
How should a physicist learn Machine Learning?
Replies
5
Views
2K
Debugging a Backprop Neural Network: Issues & Solutions
Replies
3
Views
2K
Looking for physics based simulation for data generation
Replies
6
Views
1K
Python Help solving a geometrical matching issue with Graph Neural Networks
Replies
1
Views
2K
Neural network problems with multi-input dependencies
Replies
1
Views
2K

Hot Threads

Recent Insights

Back
Top