Difference between revisions of "Optimizer"
| Line 14: | Line 14: | ||
* [http://videos.h2o.ai/watch/4Qx2eUbrsUCZ4rThjtVxeb H2O Driverless AI - Intro + Interactive Hands-on Lab - Video] | * [http://videos.h2o.ai/watch/4Qx2eUbrsUCZ4rThjtVxeb H2O Driverless AI - Intro + Interactive Hands-on Lab - Video] | ||
| − | There are many options for optimizer in Tensorflow. Optimizers are the tool to minimise [[loss]] between prediction and real value. [http://keras.io/optimizers/ Click here For a list of Keras optimizer functions.] | + | There are many options for optimizer in Tensorflow. Optimizers are the tool to minimise [[loss]] between prediction and real value. There are many, many different weights our model could learn, and brute-force testing every one would take forever. Instead, we choose an optimizer which evaluates our [[loss]] value, and smartly updates our weights. [http://keras.io/optimizers/ Click here For a list of Keras optimizer functions.] |
Revision as of 09:19, 31 August 2019
YouTube search... ...Google search
- Loss Functions
- TensorFlow Training Classes Python API
- Gradient Descent Optimization & Challenges
- Objective vs. Cost vs. Loss vs. Error Function
- H2O Driverless AI - Intro + Interactive Hands-on Lab - Video
There are many options for optimizer in Tensorflow. Optimizers are the tool to minimise loss between prediction and real value. There are many, many different weights our model could learn, and brute-force testing every one would take forever. Instead, we choose an optimizer which evaluates our loss value, and smartly updates our weights. Click here For a list of Keras optimizer functions.
Genetic Algorithm Optimization
