Very Deep (Infinite) Neural Networks - [Repo]
Benjamin Meier of Zurich University has written a report on infinite deep neural networks, which describes a meta-layer for neural networks:
"This meta-layer contains an infinite amount of sub-layers, where the network can decide at the training time how many of these layers should be used." [source]
The neural network can be optimized using gradient descent methods. The code and the library for and from this paper is available and open-sourced on github:
"The repository contains a small library that allows it to use the described meta-layer. The library is based on Keras. The library is very minimal, so not all network architectures may be created with it." [source]
It also shows how to create a basic model of the network and a few experiments so that we can get a better understanding of the network. One of these experiments receives 8 binary inputs and computes the XOR result of them, while the other experiment uses the well known MNIST.
Thinking of the practical applications of this type of architecture, I was reading through the report and I understood that the author is likely not going to keep working to develop it for reasons of time constraints, but he may be experimenting with similar models.
The author is however hopeful that someone else might be willing to pick up the work and/or ideas from it and possibly continue developing it further. You can find the library, the report, and the experiments at the following repo:
To stay in touch with me, follow @cristi
Cristi Vlad Self-Experimenter and Author
Resteemed! Man, so glad you keep pumping out good content on a daily basis! Keep it up!
i'll be honest. i'm a little bit scared of neural networks. and if you have an iphone x you have one in your pocket. mad times.
Great post i like your post thanks for sharing dear...god bless u..
Thank you very much for sharing this post because you just did not share this post. This post has written a nice way to make sure that you have a lot of benefits to share it again and thank you for sharing this post.
yeah, interesting post. but i am poor in artificial intelligence ..hahha
very interesting. we actually can fork it? how does it work?
yes, you can fork it. you use it with keras.
Helpful post i appreciate that types of posr because it helps us to gain knowledge and leading to create new ideas
Thank you please keep it up and share this type of post with us
This is some of the most informative post on Steemit. I wished more steemians shared ideas about earning more income. @hrishikesh
what?
I know right? I'm new to steemit but one thing I'm noticing is all these terrible low-effort comments that seem to be either bots or just... really low effort. At least voting helps to bring real content to the top, but then I feel bad for maybe not reading a post that just happens to be new... :(
foarte bun postul bv
Really good post!