I found more and more students asking me about neural networks and in this post I am pointing you to 4 YouTube video that can kick start your learning of this technology or simply satisfy your curiosity.
Practical applications are more complex that the classical example mentioned in this videos. Nevertheless learning how to recognize hand-written digits is always a good place to start. In other words you can consider this example as the “hello world” example for learning the basics of Neural Networks.
Modern tools for developing Neural networks such as Tensor-flow hide many of the complexities mentioned in these videos. Nevertheless a basic foundation of the concepts mentioned will speed up your developments and will foster an actual understanding of what you are doing.
These videos also point to this open book and related example code:
In thinking to what is missing in these video I would say that an introduction to genetic algorithms is probably the most important part. In a nutshell is a technique for optimizing a particular model that is inspired by biological evolution theories. As you will see in the videos the author make a lot of assumption on the neural network itself such as, for example, type of activation of the neurons, hidden layers, type of connections, way of backpropagate the feedback etc. A genetic algorithm approach could help in finding the optimal solution of these parameter.
A second aspect that is missing is the notion of “deep learning” that is a particular way of dealing with backprogation of a neural network without the need of having a train dataset.
In case you are curios to learn more these are the 2 aspects where I would encourage you in seeking more information.
In addition, if you need access to the database of hand-written digits this is a link with more information:
Let’s your friends know what you are learning :A Collection of YouTube Videos around Neural Networks. #Python example for #CodeNewbie included in the links Click To Tweet
I occasionally have some thesis related to Neural Networks, in case you are a student and you are considering learning more about that I encourage you in checking the available thesis