Artificial Intelligence, Machine Learning and Deep Learning are all the rage in the press these days, and if you want Artificial Neural Networks explained, simply and easy, and without any complex terminology or *gulp* complex maths, then you're in the right place.
If you want to be a good Data Scientist you're going to need more than just a passing understanding of what they are and what you can do with them and progress beyond the basics.
In this blog post you'll get the simplest explanation of how Artificial Neural Networks work, and we'll also introduce you to the best Artificial Neural Network courses at Udemy we can find so you can take those all-important next steps.
Disclosure: This post contains affiliate links. This means that if you click one of the links and make a purchase we may receive a small commission at no extra cost to you. As an Amazon Associate we may earn an affiliate commission for purchases you make when using the links in this page.
You can find further details in our TCs
There are loads of different methodologies, but for me I would always suggest Artificial Neural Networks as the first AI to learn - but then I've always had a soft spot for ANNs since I did my PhD on them.
They've been around since the 1970s, and until recently have only really been used as research tools in medicine and engineering. Google, Facebook and a few others, though, have realised that there are commercial uses for ANNs, and so everyone is interested in them again.
When it comes to algorithms used in AI, Machine Learning and Deep Learning, there are 3 types of learning process (aka 'training'). These are Supervised, Unsupervised and Reinforcement Learning.
Pin it for later
Need to save this for later?
Pin it to your favourite board and you can get back to it when you're ready.
Neural Networks Explained: Supervised Learning
In Supervised Learning, the inputs and outputs are matched. It's sort of like telling the network what your questions and answers are. If you give it a lot of such input:output pairs it will be able to 'learn' by example. You can then test the network by giving it a new set of questions, requiring it to make predictions of what - based on its learning - it considers the answers to be. Comparing the expected and predicted answers allows us to measure the effectiveness of the network.
Supervised learning can be used for both classification and regression problems.
For classification, the output will be a category, such as 'red' or 'blue', or 'disease' or 'no disease'. For regression, the output variable will be a continuous value, such as 'height', 'weight' or 'age'.
Neural Networks Explained: Unsupervised Learning
In Unsupervised Learning, only input data are passed to the network. It's like saying 'what do you make of these data?' and then leaving the network to try to discover some sort of organisational structure that underlies the data.
Unsupervised learning can be used for both clustering and association problems.
For clustering, the result will be that the network has determined that there are a number of groupings in the data based on specific features such as colour [R;G;B] or size [Small;Medium;Large]. For association, the network will look for rules that describe relationships between portions of your data, such as 'people that buy iPads also tend to buy iPhones' or 'smokers tend to get lung cancer'.
Neural Networks Explained: Reinforcement Learning
Reinforcement learning is a combination of supervised and unsupervised training in that a restricted amount of output information is provided about the input data. This information is usually in the form of a statement as to whether the predicted output is 'good' or 'bad', without actually telling the algorithm what it needs to do to improve - it is left to make its own decisions about this. You can think of it as a bit like training a dog or a small child - they don't understand your words yet, but they respond to rewards and punishment, and adjust their behaviour to get more sweets and fewer trips to the naughty step.
Reinforcement learning is best suited to complex problems where there are no obvious or easily programmable solution, such as in game playing (chess, backgammon, etc.) or in engineering control applications (robot control, elevator scheduling, etc.).
Artificial Neural Network Courses - How To Get Started
I never had Artificial Neural Networks explained to me. Nor was I taught. When I was learning about AI back in the *ahem*, well let's just say it was quite a while ago, you pretty much had to learn it from formal textbooks, academic papers and turning up to University lectures (when you could drag your pasty white arse out of bed at 07:30 on a cold, wet January morning).
These days you can learn about Supervised, Unsupervised and Reinforcement Learning by video course at your leisure without even getting out of bed - but don't forget to brush your teeth at least once a month...
...and I'll make it even easier for you by recommending a few courses that'll help you get a great start.
Top Artificial Neural Network Courses at Udemy - Our Pick
A while ago, when I was reviewing ANN courses at Udemy, I came across a teacher going by the name of Lazy Programmer who specialises in teaching AI stuff. After taking a look at some of his 19 courses it became clear to me that his courses interlace very nicely - in other words, if you were to take a few of his courses you would gain a really good grounding in Machine Learning.
Although I haven't managed to review all of his courses yet I wouldn't hesitate to recommend them - and better still, his courses have an excellent approval rating of 4.6 out of 5, with almost 90% of reviewers giving him a score of 4 or higher.
As I mentioned above, Supervised, Unsupervised and Reinforcement Learning are the bedrock of Machine Learning, and I would recommend that you should start your AI journey here.
So with no more further ado, here are our Top Picks for Artificial Neural Network Courses at Udemy:
Your Next Machine Learning Steps
Once you've had Artificial Neural Networks explained to you and you've mastered the basics you're going to want to do some more Deep Learning (see what I did there?).
The next steps are to jump into Deep Learning, Recurrent Neural Networks and Bayesian Machine Learning. By the time you've got the background of the first 3 Artificial Neural Network courses and then added these on top you're going to be a pretty damn good Machine Learner - and it might just make a difference to your paycheck too!
Artificial Neural Network Courses - Summary
There are loads of Artificial Neural Network courses at Udemy, not just the ones listed above. If none of these take your fancy, have a look around and I'm sure you'll find others that might just hit the spot. I also recommend taking a look at courses in Artificial Intelligence, Machine Learning and Deep Learning too.
If you discover any better courses out there, let me know - I may write about them in another blog post!
Final word - when you've done any of these courses, please return and leave some feedback and a review in the comments below. If you loved the course, great - come and tell us. If you hated it, that's great too - leave a comment saying what you didn't like about it.
At the time of writing, these courses are deeply discounted. They are usually offered for up to £/$/€ 200 each but are on sale right now for a few days at around £/$/€ 10 - so grab them while you can!
A quick reminder - once you've enrolled for a particular course, you get lifetime access to it, even when the course is updated.
All 7 posts in the series:
- Learn to be a Data Science Ninja - The Easy Way