22. Neural Networks

Neural networks have been the come-back kids of machine learning. They were invented in the 80s, but surged back into the limelight in the late 90s to become a powerful tool at the heart of deep learning. This video describes what neural networks are, how they work in materials informatics, Check out the whole materials informatics series at with workbooks and course notes available at 0:00 How do artificial neural networks differ from biological analogues 4:15 basic elements of a vanilla neural networks 7:39 notation used in neural networks 12:33 activation functions 14:08 how do neural nets learn? 16:05 concept behind backpropagation 19:20 stochastic gradient descent and learning curves 22:40 math of backpropagation 29:12 tuning neural network hyperparameters 34:47 walkthrough of pytorch notebook for neural network