
Optimizing Network Performance with Hyperparameters and Temporal Features
Explore the intricate world of hyperparameter optimization, combining temporal and non-temporal features in network construction. Dive into learning rates, optimizers, network architecture, activation functions, and more for building your first efficient network. Get ready to train a network and submit your work in this exciting homework assignment.
Download Presentation

Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Outilne Temporal feature construction Combining temporal and non temporal features in networks Hyperparameters in networks Hyperparameter optimization Homework: build and submit your first network
Hyperparameters Learning rate Constant, exponential, step decay Optimizers Momentum, Adam, Adagrad Mini batch size Early stopping Network architecture Number of hidden units, structure, residual networks Regularization: L2, L1
Hyperparameters Activation functions (Relu, Tanh) Random seeds Model averaging Data preprocessing Element wise standardization, PCA, uniformization, log, square root
Hyperparameter optimization Grid search Random search Further reading: https://arxiv.org/pdf/1206.5533v2.pdf
Announcements Next class 30.4.16 Home work : train a network and submit at least once Automatic tests Instructions Example in Predictor.py Problems tracking update this file