7:00 – 5:00 ASRC MKT
- The ONR proposal is in!
- Promoted the Odyssey thoughts to Phlog
- More BIC
- The problem posed by Heads and Tails is not that the players lack a common understanding of salience; it is that game theory lacks an adequate explanation of how salience affects the decisions of rational players. All we gain by adding preplay communication to the model is the realisation that game theory also lacks an adequate explanation of how costless messages affect the decisions of rational players. (pg 180)
- More TF crash course
- Invert the ratio for train and validation
- Add the check against test data
- Get started on LSTM w/Aaron?
-
- Mini-Course on Long Short-Term Memory Recurrent Neural Networks with Keras
- installed statsmodels 0.8.0 from here
- I think I like this better: Keras LSTM tutorial – How to easily build a powerful deep learning language model. Nope, not up to date
- How to Grid Search Hyperparameters for Deep Learning Models in Python With Keras
- Ok, the plan is that I will work on getting a hyperparameter wrapper working on a simple Keras DNN, then transpose over to Aaron’s LSTM work
- How to use a numpy ndarray (multidimensional array):
import numpy as np max = 9 dataset = np.ndarray(shape=(max, max, max)) for x in range(max): for y in range(max): for z in range(max): val = (z+1)*100 + (y+1) * 10 + x +1 dataset[x,y,z] = val print(dataset[:3,:2,3]) - Scikit-learn preprocessing is nice
- Looked at Deep Learning with Keras in Safari. It looked good, and since our network is crap and the book was $10…
- Mini-Course on Long Short-Term Memory Recurrent Neural Networks with Keras
-
viztales 