Takehiro Ishikawa

Takehiro Ishikawa, Jon Duke

This paper audits benchmark evaluation in clinical-interview depression detection through four complementary probes across DAIC/E-DAIC, CMDC, ANDROIDS, MODMA, and PDCH. First, we re-evaluate E-DAIC under strict subject-disjoint leave-one-subject-out cross-validation. A lightweight hybrid text-plus-LLM-score model reaches macro-F1 = 0.723 - the highest reported under this protocol, to our knowledge - providing a conservative out-of-fold reference point that does not depend on the privileged official holdout. Second, we test whether the E-DAIC official split supports fine-grained leaderboard rankings by sweeping 96 model configurations across modality bundles, pooling strategies, and learners. Development-side cross-validation and official-test rankings align only moderately: the best cross-validation configuration ranks twentieth on the official test, the official-test winner ranks forty-first by cross-validation, top-3 overlap is zero, and the apparent winner is rank-1 in only 32.3% of subject bootstraps. Third, we externally validate strong public CMDC and ANDROIDS baselines that achieve near-ceiling in-domain performance. Zero-shot transfer to external corpora is substantially weaker. Finally, we stress-test E-DAIC text and audio models using paired symptom-dense versus symptom-light interview slices defined by an SRDS-based annotator. Text scores rise sharply on symptom-dense slices, whereas audio scores remain nearly flat; the text-minus-audio gap is positive across all five seeds.

Takehiro Ishikawa

Background and Aims: Reproducible external benchmarks for pneumothorax-related lung ultrasound (LUS) AI are scarce, and binary lung-sliding classification may obscure clinically important signs. We therefore developed a manifest-based external benchmark and used it to test both cross-domain generalization and task validity. Methods: We curated 280 clips from 190 publicly accessible LUS source videos and released a reconstruction manifest containing URLs, timestamps, crop coordinates, labels, and probe shape. Labels were normal lung sliding, absent lung sliding, lung point, and lung pulse. A previously published single-site binary classifier was evaluated on this benchmark; challenge-state analysis examined lung point and lung pulse using the predicted probability of absent sliding, P(absent). Results: The single-site comparator achieved ROC-AUC 0.9625 in-domain but 0.7050 on the heterogeneous external benchmark; restricting external evaluation to linear clips still yielded ROC-AUC 0.7212. In challenge-state analysis, mean P(absent) ranked absent (0.504) > lung point (0.313) > normal (0.186) > lung pulse (0.143). Lung pulse differed from absent clips (p=0.000470) but not from normal clips (p=0.813), indicating that the binary model treated pulse as normal-like despite absent sliding. Lung point differed from both absent (p=0.000468) and normal (p=0.000026), supporting its interpretation as an intermediate ambiguity state rather than a clean binary class. Conclusion: A manifest-based, multi-source benchmark can support reproducible external evaluation without redistributing source videos. Binary lung-sliding classification is an incomplete proxy for pneumothorax reasoning because it obscures blind-spot and ambiguity states such as lung pulse and lung point.

Takehiro Ishikawa

We investigate how to couple a learnable brain-like'' controller to a cell-like'' Gray--Scott substrate to steer pattern formation with minimal effort. A compact convolutional policy is embedded in a differentiable PyTorch reaction--diffusion simulator, producing spatially smooth, bounded modulations of the feed and kill parameters ($ΔF$, $ΔK$) under a warm--hold--decay gain schedule. Training optimizes Turing-band spectral targets (FFT-based) while penalizing control effort ($\ell_1/\ell_2$) and instability. We compare three regimes: pure reaction--diffusion, NN-dominant, and a hybrid coupling. The hybrid achieves reliable, fast formation of target textures: 100% strict convergence in $\sim 165$ steps, matching cell-only spectral selectivity (0.436 vs.\ 0.434) while using $\sim 15\times$ less $\ell_1$ effort and $>200\times$ less $\ell_2$ power than NN-dominant control. An amplitude sweep reveals a non-monotonic Goldilocks'' zone ($A \approx 0.03$--$0.045$) that yields 100\% quasi convergence in 94--96 steps, whereas weaker or stronger gains fail to converge or degrade selectivity. These results quantify morphological computation: the controller seeds then cedes,'' providing brief, sparse nudges that place the system in the correct basin of attraction, after which local physics maintains the pattern. The study offers a practical recipe for building steerable, robust, and energy-efficient embodied systems that exploit an optimal division of labor between centralized learning and distributed self-organization.

Takehiro Ishikawa

Recent advancements in QML and SNNs have generated considerable excitement, promising exponential speedups and brain-like energy efficiency to revolutionize AI. However, this paper argues that they are unlikely to displace DNNs in the near term. QML struggles with adapting backpropagation due to unitary constraints, measurement-induced state collapse, barren plateaus, and high measurement overheads, exacerbated by the limitations of current noisy intermediate-scale quantum hardware, overfitting risks due to underdeveloped regularization techniques, and a fundamental misalignment with machine learning's generalization. SNNs face restricted representational bandwidth, struggling with long-range dependencies and semantic encoding in language tasks due to their discrete, spike-based processing. Furthermore, the goal of faithfully emulating the brain might impose inherent inefficiencies like cognitive biases, limited working memory, and slow learning speeds. Even their touted energy-efficient advantages are overstated; optimized DNNs with quantization can outperform SNNs in energy costs under realistic conditions. Finally, SNN training incurs high computational overhead from temporal unfolding. In contrast, DNNs leverage efficient backpropagation, robust regularization, and innovations in LRMs that shift scaling to inference-time compute, enabling self-improvement via RL and search algorithms like MCTS while mitigating data scarcity. This superiority is evidenced by recent models such as xAI's Grok-4 Heavy, which advances SOTA performance, and gpt-oss-120b, which surpasses or approaches the performance of leading industry models despite its modest 120-billion-parameter size deployable on a single 80GB GPU. Furthermore, specialized ASICs amplify these efficiency gains. Ultimately, QML and SNNs may serve niche hybrid roles, but DNNs remain the dominant, practical paradigm for AI advancement.