Differences

This shows you the differences between two versions of the page.

--- public:t-720-atai:atai-21:learning [2021/09/02 09:18] – [Data, Information, Knowledge] thorisson
+++ public:t-720-atai:atai-21:learning [2024/04/29 13:33] (current) – external edit 127.0.0.1
@@ Line 136: / Line 136: @@
 |   Input Data   | Continuous and discrete variables.    |
 |   Output Data   | Continuous and discrete variables.    |
-|   Max. # I/O Vars.    | Very high (limited by CPU and BW).     |
+|   Max. # I/O Vars.    | Very high (possibly limited by CPU and BW only).     |
-|   Min. Cycles   | Typical numbers 4k-10k. \\ Depends on data complexity and number of layers in the ANN.     |
+|   Min. Training Cycles   | Typical numbers 4k-10k. \\ Depends on data complexity and number of layers in the ANN.     |
 |  Training  | Off-task. Learning turned off when fully trained.    |
 |  Training Style  | Training phase BILL (before it leaves the lab); discrete training steps.   |
 |  \\ Training Signal  | Supervised learning: Explicit "error signal propagation" after every turn, generated from pre-categorized examples and outcomes. \\ Unsupervised: explicit "error signal propagation" after every turn, auto-generated.  |
-|  Hyper-Parameters  | - Learning Rate and many others   |
+|  Hyper-Parameters  | - Learning Rate, Exploration/Exploitation, and many others   |
 |  Strengths  | Handles complex data sets. \\    |
 |  Scalability  | Unpredictable behavior under data drift AILL (after it leaves the lab). \\ Must be trained BILL (unpredictable learning AILL). \\    |