Difference between revisions of "Loss"

From
Jump to: navigation, search
Line 5: Line 5:
 
|description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools  
 
|description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools  
 
}}
 
}}
[http://www.youtube.com/results?search_query=optimizers+deep+learning YouTube search...]
+
[http://www.youtube.com/results?search_query=loss+deep+learning YouTube search...]
[http://www.google.com/search?q=optimizers+machine+learning+ML+artificial+intelligence ...Google search]
+
[http://www.google.com/search?q=loss+machine+learning+ML+artificial+intelligence ...Google search]
  
 
* [[Optimizer]] Parameter
 
* [[Optimizer]] Parameter
* [https://www.tensorflow.org/api_guides/python/train TensorFlow Training Classes Python API]
+
* [http://github.com/llSourcell/loss_functions_explained Loss Functions Explained | Siraj Raval]
* [[Gradient Descent Optimization & Challenges]]
 
* [[Objective vs. Cost vs. Loss vs. Error Function]]
 
* [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.  
+
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.]
  
<youtube>cJA5IHIIL30</youtube>
+
<youtube>IVVVjBSk9N0</youtube>
<youtube>ttE0F7fghfk</youtube>
+
<youtube>78vq6kgsTa8</youtube>
<youtube>Ym1m4Bh14ps</youtube>
+
<youtube>Skc8nqJirJg</youtube>
<youtube>hXtEQavhrLk</youtube>
+
<youtube>h7iBpEHGVNc</youtube>
<youtube>JXQT_vxqwIs</youtube>
 
 
 
== Genetic Algorithm Optimization ==
 
 
 
<youtube>lV8gqnVujjY</youtube>
 
<youtube>giBAxWeuysM</youtube>
 

Revision as of 08:37, 31 August 2019

YouTube search... ...Google search

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. here For a list of Keras loss functions.