From VLSI testing to motivated learning: cognitive architectures and open-source associative memory (Rzeszow, PL)
2
papers here
1
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
31
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-17) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Output is not scored: this snapshot lacks the complete publication-volume data the axis needs. Output would measure total and per-year scholarly production, enabling productivity to be compared against field norms once fuller bibliographic records are linked.
Impact—
Impact is not scored: the citation-based measures behind this axis were insufficient in the current snapshot. Impact would capture the citation influence and field-normalized standing of the work, and can be estimated once complete citation records are linked.
Focus100/100
Focus scores 100/100, the strongest axis in this profile. The current record's field classification is single-threaded — fieldDist lists computational neuroscience as the only field — and both reviewed 2026 papers sit in machine intelligence and neural computation. Historically, though, the five indexed topic clusters (led by Neural Networks and Applications at 71 and VLSI and Analog Circuit Testing at 40) show a deliberate, long-held pairing of circuit engineering with cognitive modeling rather than scattered topic-hopping.
Collaboration28/100
Collaboration scores 28/100, the profile's weakest social signal: the current record lists only 3 distinct coauthors, and on the reviewed papers Starzyk holds middle and last author positions without corresponding authorship. His recurring partners — Przemysław Stokłosa, Paweł Raif, and Wiesław L. Galus — point to small, stable Polish teams rather than large international consortia. For collaborators this means direct access to the lead thinker, but little evidence of distributed multi-institutional project work.
Activity70/100
Activity scores 70/100. The snapshot counts 10 works in the last three years, and the yearly record runs from 1975 through 2026, with historic peaks of 40 (2014), 29 (2002), and 21 (2003). Recent years show steady, modest volume — 5 (2020), 5 (2023), 3 (2025), and 6 (2026) — consistent with a senior researcher who keeps producing at a measured pace rather than sprinting.
Reproducibility20/100
Reproducibility scores 20/100, computed across one assessed paper (reproMean 20). The evidence is bimodal: SSAKG 2.0 ships open-source code and reaches medium readiness, though Evolve flags untested speed claims and absent NLTK/mRNA results; the MEM model is purely definitional — no simulations, data, or proofs — and rates low. With only one paper assessed, treat this axis as indicative rather than settled.
Research summary
Janusz A. Starzyk, based at the University of Information Technology and Management in Rzeszow (Poland), has a bibliographic record spanning two long-running strands: circuit engineering and test systems on one side, neural and cognitive computation on the other. The indexed topic profile leads with Neural Networks and Applications (71), followed by VLSI and Analog Circuit Testing (40), Analog and Mixed-Signal Circuit Design (35), Psychiatry, Mental Health, Neuroscience (33), and Engineering and Test Systems (32). The snapshot reports an h-index of 31 and an i10 index of 56; annual counts reach back to 1975 and peak at 40 in 2014 (29 in 2002, 21 in 2003), with 10 works in the last three years. His 2026 output shows the current agenda: a purely theoretical mathematical model of the Motivated Emotional Mind (MEM) — an embodied, affect-driven architecture built on motivated learning, interoception, and allostatic regulation — and SSAKG 2.0, an open-source package for structural associative sequence memory with context-based retrieval. Evolve's read is that the theory is coherent but unvalidated by simulation or data, while the software reports large error gains yet leaves speed claims and promised benchmarks untested. Collaboration is concentrated (3 distinct coauthors) and reproducibility signals are mixed-to-low.
Collaboration pattern
The visible collaboration footprint is compact: 3 distinct coauthors in the current record, with Przemysław Stokłosa, Paweł Raif, and Wiesław L. Galus as recurring partners — reflected in a collaboration score of 28/100. On the reviewed 2026 preprints he appears as a middle and last author, not corresponding, suggesting a senior-contributor role within small Polish teams around Rzeszow rather than large multi-institution consortia.
Research keywords
Highlights
Formalizing the Motivated Emotional Mind (MEM) as an embodied cognitive system
SSAKG 2.0: open-source structural associative memory with context-based retrieval
Timeline
- 1975Earliest year in the indexed record (1 counted item); the bibliometric trail begins in the mid-1970s.
- 2002Annual counts spike to 29 in the indexed record, with 21 following in 2003 — the densest stretch of the 2000–2003 run.
- 2014The highest annual count in the record: 40, the bibliometric peak across the whole 1975–2026 span.
- 20205 counted items; steady recent-volume years continue with 5 in 2023 and 3 in 2025.
- 2026Two arXiv preprints enter the Evolve catalog: the MEM mathematical model (last author) and SSAKG 2.0 (middle author).
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometric data is OpenAlex-derived (identity: openalex) and name-resolved from public bibliographic records; the semantics of countsByYear (works vs. citations) are not specified in the snapshot.
- Radar could not score the output and impact axes in this snapshot; the reported h-index (31) and i10 index (56) are quoted verbatim from the raw snapshot.
- Evolve's qualitative review covers only two 2026 arXiv preprints, and the reproducibility score rests on a single assessed paper (reproMean 20, reproPapers 1).
- Recorded counts extend into 2026, so the current-year record may still be incomplete.