I will have a short talk prepared about neural networks, followed by a demonstration Keras in Python as applied to the MNIST digit recognition task Michael talked about today. (https://www.kaggle.com/c/digit-recognizer).
You can take a look at my Kaggle notebook here (please upvote it if you find it useful). (https://www.kaggle.com/danielelton/digit-recognizer/keras-cnn-with-explanation)
I'd also like to talk more about the Two Sigma Financial Modeling Challenge (https://www.kaggle.com/c/two-sigma-financial-modeling)on Kaggle.
One topic I'd like to get into eventually is hyperparameter optimization, in particular using Bayesian optimization.
I am also compiling a list of good machine learning resources (online courses, textbooks, blog posts, and websites with problems and challenges to test your chops).
If you would like to present something on Monday or at a future meetup, please send me an email. Your presentation can be as short and as informal as you want.