Neuronal Networks PART I Introduction

in #neuronalnetwork7 years ago (edited)

Hey Community,

as i promised in my first post, ich will start to give you a rough overview of
neuronal networks an what they are able to do.

This post will be posted in serveral Parts starting here with the Indroduction.

You can find all posts in this List:

PartHeadlineSteemit Link:
IIntroductionCurrent Document
IIUnitshttps://steemit.com/science/@haggy2k3/neuronal-networks-part-ii-units
IIIConnectionshttps://steemit.com/science/@haggy2k3/neuronal-networks-part-iii-connections
IVInputshttps://steemit.com/science/@haggy2k3/neuronal-networks-part-iv-inputs
VActivities and Outputs
VITraining and Test
VIIMetrics
VIIILearning Rules
IXTypes of NN
XFeatures of NN
XIUse Cases
XIIBonus: Getting started with Membrain


Introduction

Neural networks refer to the neural network of the human brain. This serves as an analogy and inspiration for computer simulated artificial neural networks. However, this analogy is often no longer in the foreground in today's work on neural networks.
The first ones to study neural networks were Warren McCulloch and Walter Pitts in 1943 with their formal model of the neuron.


Warren McCulloch


Walter Pitts

The work with and to neural networks has increased since 1986 very strong. There are now numerous scientific journals that deal primarily with this topic. "Neurocomputing", "Neural Computation" or "Neural Networks". Meanwhile, the
scope of the method can be divided into two broad areas: Artificial neural Networks, which are modeled to better understand human behavior and experience or the functioning of the human brain. Artificial neural networks, which serve concrete application problems from areas such. B. Statistics, economics, engineering and many other areas to solve. Overall, the idea of ​​neural networks exerts a very high fascination on many people. This learning aid should on the one hand try to transfer this enthusiasm to you. At the same time, however, it should also be shown that neural networks are nothing more than matrix calculations.

If you like this post and you want to read more please upvote an follow my blog.

Best regards

Haggy2k3

Sort:  

Awesome look into the history of neural networks! Machine learning is one of my passions, and I've written two neural networks so far for small games of mine trying to better learn them. Neural networks, as well as genetic algorithms or back propagation for learning, are insanely useful, especially for scenarios where the data is noisy/less clear.

I'm excited to see more of your posts! I was going to write blogs about this actually, but I decided not to put too much on my plate and focus on blockchain research for now.

I think this is a fantastic topic, I can't wait to see more of what you put out :)

Thx for your Feedback i just followed you cause i have a great new project where i want to connect blockchain tech and machine learning... later i will build up a community project for that. Maybe we could work together in future.

I would love to hear about that project, I've been wondering what useful use cases there are for machine learning on a blockchain. I'd love to hear your scenario sometime!

I have a lot on my plate over the next little while, but I'm sure in the future we could make something work :)

Coin Marketplace

STEEM 0.20
TRX 0.13
JST 0.030
BTC 65641.09
ETH 3479.54
USDT 1.00
SBD 2.50