digitado

Semi-supervised learning aims to infer class labels using only a small fraction of labeled data. In graph-based semi-supervised learning, this is typically achieved through label propagation to predict labels of unlabeled nodes. However, in real-world applications, data often arrive incrementally in batches. Each time a new batch appears, reapplying the traditional label propagation algorithm to recompute all labels is redundant, computationally intensive, and inefficient. To address the absence of an efficient label propagation update method, we propose DynLP, […]

Ver mais

You spend weeks getting your WordPress site just right. The colors match your brand. The copy reads well. The contact form works. You launch, share it on social media, maybe even run a few ads. And then… nothing changes. For years. This is the reality for most WordPress sites on the internet. According to W3Techs, WordPress powers roughly 43% of all websites. That is hundreds of millions of sites. But a massive chunk of them are running outdated […]

Ver mais

We decompose the spectral edge — the dominant direction of the Gram matrix of parameter updates — into its gradient and weight-decay components during grokking in two sequence tasks (Dyck-1 and SCAN). We find a sharp two-phase lifecycle: before grokking the edge is gradient-driven and functionally active; at grokking, gradient and weight decay align, and the edge becomes a compression axis that is perturbation-flat yet ablation-critical (>4000x more impactful than random directions). Three universality classes emerge (functional, mixed, […]

Ver mais

Testing whether AI can replace your Scrum Master (spoiler: it can’t) Here’s a question that’s been bouncing around tech Twitter: Can AI do sprint planning? Not “can it generate user stories” or “can it estimate story points” — I mean actual, realistic sprint planning that a human Scrum Master would do. The kind where you account for developer velocity, context switching, technical debt, and all the messy reality of building software. I decided to find out by throwing […]

Ver mais

Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another. Yet, developing artificial intelligence systems capable of robust human-like analogical reasoning has proven difficult. In this work, we train transformers using Meta-Learning for Compositionality (MLC) on an analogical reasoning task (letter-string analogies) and assess their generalization capabilities. We find that letter-string analogies become learnable when guiding the models to attend to the most informative problem elements […]

Ver mais

After 20 dead versions and about 2 years of work, my RL agent (NASMU) passed its walk-forward backtest across 2020–2026. But the most interesting part wasn’t the results — it was what the model actually learned. The setup: – PPO + xLSTM (4 blocks), BTC/USDT 4h bars – 35 features distilled from López de Prado, Hilpisch, Kaabar, Chan and others – Triple Barrier labeling (TP/SL/Timeout) – HMM for regime detection (bull/bear/sideways) – Running on a Xeon E5-1650 v2 […]

Ver mais