Videos by Brandon Rohrer: https://www.youtube.com/watch?v=Q9Z20HCPnww - in this video I liked how he makes a connection between actual neurons and neural networks. Weights mean the strength of connections between neurons. Connection between dendrite of one neuron and axon of another is called "synapse". Although the shawarma guy example was not easy for me to understand... The other one "How Neural Networks work https://www.youtube.com/watch?v=ILsA4nyG7I0 has a pretty simple step-by-step explanation of NN workflow based on a simple example of 2x2 "camera". Good explanation of how weights work, backpropagation, sigmoid, ReLU, etc. A friendly introduction to Deep Learning and Neural Networks by Luis Serano (https://www.youtube.com/watch?v=BR9h47Jtqyw) is easy to understand and really friendly for the first 2/3, but then he jumps to calculating probabilities, errors, etc. and it becomes harder to follow. In general, it's a common problem of most of the
A friend of mine, who works for NVIDIA, got me interested in Machine Learning, Deep Learning and everything around it. So I decided--why not? Let's learn something about this magic technologies and--who knows--it might be a new direction in my life. I decided to keep this blog as my learning diary because I know from experience: something that is really hard to understand in the beginning, becomes pretty easy later and you forget about your struggles. If you are going to explain this hard things to somebody later (I am), it's very valuable to remember/record your very early experience: what was easy, what was hard, some "gotchas" on your way. In this blog I'll be collecting my experience while I'm learning: what courses I am taking, what I liked and what I didn't. I hope it might help someone. At least I know it will help me some time later.