| Both sides previous revisionPrevious revisionNext revision | Previous revision |
| public:t-720-atai:atai-21:learning [2021/09/02 09:17] – thorisson | public:t-720-atai:atai-21:learning [2024/04/29 13:33] (current) – external edit 127.0.0.1 |
|---|
| | Data | Stored, committed-to //Measurement//. \\ Data that can be/is formatted and used for a purpose. | | | Data | Stored, committed-to //Measurement//. \\ Data that can be/is formatted and used for a purpose. | |
| | Information | A set of //Data// grouped for a purpose. | | | Information | A set of //Data// grouped for a purpose. | |
| | \\ Knowledge | A set of interlinked information that can be used to plan, produce action, and interpret new information. \\ Actionable information. Information that can be used to get stuff done. | | | Knowledge | A set of interlinked information that can be used to plan, produce action, and interpret new information. \\ Actionable information. Information that can be used to get stuff done. | |
| |
| \\ | \\ |
| | Input Data | Continuous and discrete variables. | | | Input Data | Continuous and discrete variables. | |
| | Output 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 | Off-task. Learning turned off when fully trained. | |
| | Training Style | Training phase BILL (before it leaves the lab); discrete training steps. | | | 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. | | | \\ 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. \\ | | | Strengths | Handles complex data sets. \\ | |
| | Scalability | Unpredictable behavior under data drift AILL (after it leaves the lab). \\ Must be trained BILL (unpredictable learning AILL). \\ | | | Scalability | Unpredictable behavior under data drift AILL (after it leaves the lab). \\ Must be trained BILL (unpredictable learning AILL). \\ | |
