Difference between revisions of "Loss"
Line 9: | Line 9: | ||
* [[Optimizer]] Functions | * [[Optimizer]] Functions | ||
+ | * [[Objective vs. Cost vs. Loss vs. Error Function]] | ||
+ | * [http://towardsdatascience.com/common-loss-functions-in-machine-learning-46af0ffc4d23 Common Loss functions in machine learning | Ravindra Parmar - Towards data Science] | ||
* [http://github.com/llSourcell/loss_functions_explained Loss Functions Explained | Siraj Raval] | * [http://github.com/llSourcell/loss_functions_explained Loss Functions Explained | Siraj Raval] | ||
+ | * [http://ml-cheatsheet.readthedocs.io/en/latest/loss_functions.html Loss Functions | ML Cheatsheet] | ||
There are many options for loss in Tensorflow (Keras). The actual optimized objective is the mean of the output array across all datapoints. Loss is one of the two parameters required to compile a model. [http://keras.io/losses/ Click here For a list of Keras loss functions.] | There are many options for loss in Tensorflow (Keras). The actual optimized objective is the mean of the output array across all datapoints. Loss is one of the two parameters required to compile a model. [http://keras.io/losses/ Click here For a list of Keras loss functions.] | ||
+ | |||
+ | ---- | ||
+ | ::<code> model.compile([[optimizer]]='[[Average-Stochastic Gradient Descent (SGD) Weight-Dropped LSTM (AWD-LSTM) |sgd]]'. loss='mean_squared_error')</code> | ||
+ | ---- | ||
+ | |||
<youtube>IVVVjBSk9N0</youtube> | <youtube>IVVVjBSk9N0</youtube> |
Revision as of 09:04, 31 August 2019
YouTube search... ...Google search
- Optimizer Functions
- Objective vs. Cost vs. Loss vs. Error Function
- Common Loss functions in machine learning | Ravindra Parmar - Towards data Science
- Loss Functions Explained | Siraj Raval
- Loss Functions | ML Cheatsheet
There are many options for loss in Tensorflow (Keras). The actual optimized objective is the mean of the output array across all datapoints. Loss is one of the two parameters required to compile a model. Click here For a list of Keras loss functions.