An MIT team let a randomly connected network self-organize its learning machinery from simple rules such as strengthening connections that fire together, matching backpropagation-designed networks on image classification.
Feed-forward neural networks trained on state-to-state rate coefficients for 24 linear molecules colliding with para-H2 extend existing datasets to 500 K and 696 cm-1 and give a first estimate within a factor of 3 for CS and CF+, which were excluded from training entirely.
Addressing the difficulty of characterising depression in Alzheimer's disease (AD), this study built an explainable multimodal framework integrating linguistic and acoustic features from elicited picture-description speech, used a source-informed cross-dataset transfer strategy to compensate for the absence of directly observed depression labels in the target AD cohort, identified two distinct speech sub-phenotypes via unsupervised clustering, found that one cluster showed mathematical proximity (cosine similarity in a shared latent space) to the depression centroid of a depression-labelled source corpus, then validated cluster separability with a proxy supervised classification task in which the retained multimodal artificial neural network achieved 92.
Using retrospective data from 100 patients who underwent transsphenoidal endoscopic pituitary tumor resection between 2016 and 2025, the study extracted 22 preoperative variables and developed and evaluated an artificial neural network and a random forest model against R², MAE, RMSE, and clinical accuracy thresholds of ±30 and ±45 minutes; the ANN outperformed random forest with a test-set MAE of 0.636 hours (about 38 minutes), 63.3% of predictions fell within ±30 minutes and 76.7% within ±45 minutes, and key predictors included tumor recurrence, distance from the third ventricle floor, and the cinch sign, which the authors present as objective evidence for nursing scheduling and operating room planning.
You’re all caught up