The art of representation: memory reduction and noise tolerance in a neural network vision system
Bibliographic record
Abstract
The Feature Cerebellar Model Arithmetic Computer (FCMAC) is a multiple-input-single-output neural network that can provide three-degree-of-freedom (3-DOF) pose estimation for a robotic vision system. The FCMAC provides sufficient accuracy to enable a manipulator to grasp an object from an arbitrary pose within its workspace. The network learns an appearance-based representation of an object by storing coarsely quantized feature patterns. As all unique patterns are encoded, the network size grows uncontrollably. A new architecture is introduced herein, which combines the FCMAC with an Adaptive Resonance Theory (ART) network. The ART module categorizes patterns observed during training into a set of prototypes that are used to build the FCMAC. As a result, the network no longer grows without bound, but constrains itself to a user-specified size. Pose estimates remain accurate since the ART layer tends to discard the least relevant information first. The smaller network performs recall faster, and in some cases is better for generalization, resulting in a reduction of error at recall time. The ART-Under-Constraint (ART-C) algorithm is extended to include initial filling with randomly selected patterns (referred to as ART-F). In experiments using a real-world data set, the new network performed equally well using less than one tenth the number of coarse patterns as a regular FCMAC. The FCMAC is also extended to include real-valued input activations. As a result, the network can be tuned to reject a variety of types of noise in the image feature detection. A quantitative analysis of noise tolerance was performed using four synthetic noise algorithms, and a qualitative investigation was made using noisy real-world image data. In validation experiments, the FCMAC system outperformed Radial Basis Function (RBF) networks for the 3-DOF problem, and had accuracy comparable to that of Principal Component Analysis (PCA) and superior to that of Shape Context Matching (SCM), both of which estimate orientation only.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".