Hybrid Sentient Canopy: An implementation and visualization of proprioreceptive curiosity-based machine learning
Bibliographic record
Abstract
This paper describes the development of a sentient canopy that interacts with human visitors by using its own internal motivation. Modular curiosity-based machine learning behaviour is supported by a highly distributed system of microprocessor hardware integrated within interlinked cellular arrays of sound, light, kinetic actuators and proprioreceptive sensors in a resilient physical scaffolding system. The curiosity-based system involves exploration by employing an expert system composed of archives of information from preceding behaviours, calculating potential behaviours together with locations and applications, executing behaviour and comparing result to prediction. Prototype architectural structures entitled Sentient Canopy and Sentient Chamber developed during 2015 and 2016 were developed to support this interactive behaviour, integrating new communications protocols and firmware, and a hybrid proprioreceptive system that configured new electronics with sound, light, and motion sensing capable of internal machine sensing and externally- oriented sensing for human interaction. Proprioreception was implemented by producing custom electronics serving photoresistors, pitch-sensing microphones, and accelerometers for motion and position, coupled to sound, light and motion-based actuators and additional infrared sensors designed for sensing of human gestures. This configuration provided the machine system with the ability to calculate and detect real-time behaviour and to compare this to models of behaviour predicted within scripted routines. Testbeds located at the Living Architecture Systems Group/Philip Beesley Architect Inc. (LASG/PBAI, Waterloo/Toronto), Centre for Information Technology (CITA, Copenhagen) National Academy of Sciences (NAS) in Washington DC are illustrated.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".