- A feedback-driven adaptive learning binary-classifier that based on error input autonomously alters its decision boundary by implementing Max-Initialized Decremental Search (MIDS) and resets the control loop for repeated adaptive cycles.
🤖 Adaptive learning system implementing MIDS algorithm
- Stage 0 (v0.x): Strict Boolean pattern relation analyzer. No learning, no noise tolerance, decision boundaries fixed by structural wiring.
- Stage 1 (v1.0): Popcount based similarity and a variable threshold to alter the decision boundary. Introduces noise tolerance and ability to change the decision output without structural changes.
- Stage 2 (v1.1): Cybernetic Feedback-driven adaptive learning. System alters its decision boundary based on external feedback to correct its decision output.
- MIDS Algorithm
⟵ DEVELOPED - SATU Algorithm
- MIDS Algorithm
-
Version 0: A pattern relation analyzer that classifies how an input pattern relates to a stored pattern, enforces rule based recognition rather than learning.- Detector_v0.0 -> Recognizes the exact pattern and sub-patterns if they are inside the boundary set up by weights-grid.
- Detector v0.1 -> Recognizes the exact pattern and super-patterns if they are outside the boundary set up by weights-grid.
- Detector v0.2 -> Classifies the input as a sub-pattern, super-pattern, anti-pattern or equivalence precisely through a 2-POV logical analysis.
-
Version 1: Pop-count based judgement against a variable Threshold instead of perfect equivalence check and cybernetic feedback-driven adaptive learning.- Detector_v1.0 -> Recognizes the pattern if total number of matched pixels are greater than the set threshold which can vary giving us ability to control the decision output.
- Detector_v1.1 -> A feedback-driven adaptive system that autonomously adjusts its decision boundary to correct its output, using algorithms optimized for hardware constraints.
🧩 Block Diagram - Detector_v1.0 (Manually Alterable Decision Boundary)
| Property | MIDS | SATU |
|---|---|---|
| Correction Speed | O(N) | O(1) |
| State Awareness | None | Current & desired output |
| Direction | Always starts from max, decrements | Sets to M or M-1 as needed |
| Initialization Bias | Instant correction for false positives | None |
| Hardware Complexity | Low - decrementer only | Higher - decrementer + decision logic |
| Guaranteed Convergence | Yes | Yes |
⏱️ Correction Speed Complexity Comparison
Equivalence & Sub-Pattern Recognition 🔹
Equivalence & Super-Pattern Recognition 🟦
Equivalence & Super & Sub & Anti-Pattern Recognition 🔹🟦
Manually Alterable Decision Boundary ⚖️
To verify hardware realizability, all detector variants were synthesized using Yosys. The resulting gate-level netlists were analyzed to compare architectural complexity and resource utilization across the evolution of the Cybernetic Classifier.
| Version | Module | Cells | Key Hardware Structures | Purpose |
|---|---|---|---|---|
| Detector v0.0 | Eq/Sub Recognizer | 8 | 3 AND, 2 NOT, OR, Reduction-AND | Recognizes exact matches and input sub-patterns of the reference pattern |
| Detector v0.1 | Eq/Super Recognizer | 8 | 3 AND, 2 NOT, OR, Reduction-AND | Recognizes exact matches and input super-patterns of the reference pattern |
| Detector v0.2 | Multi-POV Classifier | 28 | Dual Recognition Engines, Decision Logic, 11 MUXes | Classifies input-reference relationships as SUB, SUPER, EQ, or ANTI |
| Detector v1.0 | Pop-Count Recognition | 22 | 15 Adders, Comparator, Threshold Logic | Similarity-based recognition with a manually alterable decision boundary |
| Category | Result |
|---|---|
| Smallest Design | Eq/Sub Recognizer (8 cells) |
| Smallest Design | Eq/Super Recognizer (8 cells) |
| Most Arithmetic-Heavy | Pop-Count Recognition (15 adders) |
| Most Decision-Heavy | Multi-POV Classifier (11 MUXes) |
| Largest Design | Multi-POV Classifier (28 cells) |
All detector variants were successfully synthesized using Yosys.
Detector_v1.0 Synthesized - Yosys ✅
- Stage 2 in progress - MIDS: Developed ✓ | SATU: In Development
Download → download_repos.bat
Double-click it and pick the repo(s) you want.
Download → download_repos.sh
bash
chmod +x download_repos.sh
./download_repos.sh
Always downloads the latest version.
- Source code and HDL files are licensed under the MIT License.
- Documentation, diagrams, images, and PDFs are licensed under Creative Commons Attribution 4.0 (CC BY 4.0).