What is Deep Learning?
Everyone has heard of it, but few know what it actually is.
The official definition is:
Deep Learning (DL) is a machine learning method using artificial neural networks.
Okay, so far so good.
But what is machine learning?
Machine Learning (ML) is one of the most common techniques in Artificial Intelligence and uses algorithms to analyse data, learn from it and make statements and predictions, and so on, and so on….
Aha, so artificial intelligence. But how does that work exactly?
Artificial intelligence (AI) is essentially based on the calculation of probabilities and the recognition of patterns. Put simply, machines are taught abilities and instincts that living beings, i.e. biological intelligence, already possess from birth.
Well, it’s not quite that easy, but it sounds a bit more logical, doesn’t it?
But let’s go back to Deep Learning.
We already know that Deep Learning uses artificial neural networks. Tasks such as face or speech recognition – no problem for humans, but so far mathematically impossible to represent – have so far posed a major challenge to artificial intelligence. For programming using the conventional procedural method, a programmer develops a programme code from a sequence of ifs and thens. Artificial neural networks (ANNs) are trained so that they can independently establish relationships between different pieces of information. For this training, samples must be shown to the system. Only then can the deep learning system independently find the decisions in its “hidden layer” – i.e. the layers between input and output.
