https://cluster-site.onrender.com/tags/machine-learning/ Recent content in Machine-Learning on Tenu Tech Brief Hugo -- 0.146.0 en-us Tue, 24 Feb 2026 06:06:04 +0000 https://cluster-site.onrender.com/posts/linear-reservoir-a-diagonalization-based-optimization/ Tue, 24 Feb 2026 05:00:00 +0000 https://cluster-site.onrender.com/posts/linear-reservoir-a-diagonalization-based-optimization/ • Diagonalize recurrent matrix to transform reservoir dynamics into eigenbasis, eliminating costly matrix multiplication. • Achieves per-step computational complexity reduction fro https://cluster-site.onrender.com/posts/ra-qa-towards-respiratory-audio-based-health-question-answering/ Tue, 24 Feb 2026 05:00:00 +0000 https://cluster-site.onrender.com/posts/ra-qa-towards-respiratory-audio-based-health-question-answering/ • RA-QA dataset: 7.5M QA pairs, 60+ attributes, 3 question types. • Curated 11 respiratory audio datasets, first multimodal QA resource bridging audio and natural language. • Bench https://cluster-site.onrender.com/posts/trojans-in-artificial-intelligence-trojai-final-report/ Mon, 23 Feb 2026 05:00:00 +0000 https://cluster-site.onrender.com/posts/trojans-in-artificial-intelligence-trojai-final-report/ • IARPA TrojAI program tackles AI trojan backdoor vulnerability in modern AI systems. • Found detection via weight analysis and trigger inversion techniques to identify hidden back https://cluster-site.onrender.com/posts/simple-baselines-are-competitive-with-code-evolution/ Fri, 20 Feb 2026 05:00:00 +0000 https://cluster-site.onrender.com/posts/simple-baselines-are-competitive-with-code-evolution/ • Code evolution uses LLMs to mutate code, yet lacks baseline comparisons. • Authors test two simple baselines across math bounds, agentic scaffolds, and ML contests. • Baselines m https://cluster-site.onrender.com/posts/distributedestimator-distributed-training-of-quantum-neural-networks-via-circuit-cutting/ Thu, 19 Feb 2026 05:00:00 +0000 https://cluster-site.onrender.com/posts/distributedestimator-distributed-training-of-quantum-neural-networks-via-circuit-cutting/ • Circuit cutting splits large quantum circuits into smaller subcircuits, enabling classical reconstruction of expectation values. • Prior studies focused on subcircuit counts and https://cluster-site.onrender.com/posts/teaching-machines-to-quiet-the-noise-in-quantum-computers/ Mon, 02 Feb 2026 06:05:00 +0000 https://cluster-site.onrender.com/posts/teaching-machines-to-quiet-the-noise-in-quantum-computers/ • IIT Madras team uses machine learning to pinpoint noise sources in quantum computers. • Neural networks trained on synthetic data predict noise features with minimal accuracy los https://cluster-site.onrender.com/posts/introducing-waypoint-1-real-time-interactive-video-diffusion-from-overworld/ Tue, 20 Jan 2026 00:00:00 +0000 https://cluster-site.onrender.com/posts/introducing-waypoint-1-real-time-interactive-video-diffusion-from-overworld/ • Waypoint‑1 is Overworld’s real‑time interactive video diffusion model, controllable via text, mouse, and keyboard. • Trained on 10,000 hours of diverse video‑game footage with co https://cluster-site.onrender.com/posts/detecting-faulty-deployments-our-journey-from-unlabeled-data-to-supervised-learning/ Tue, 03 Jun 2025 00:00:00 +0000 https://cluster-site.onrender.com/posts/detecting-faulty-deployments-our-journey-from-unlabeled-data-to-supervised-learning/ • Deployments drive 70% of incidents, making rapid fault detection critical for modern DevOps. • Datadog’s Automatic Faulty Deployment Detection uses APM telemetry to spot problema https://cluster-site.onrender.com/posts/enhancing-neural-network-training-at-yelp-achieving-1400x-speedup-with-wideanddeep/ Wed, 22 Jan 2025 00:00:00 +0000 https://cluster-site.onrender.com/posts/enhancing-neural-network-training-at-yelp-achieving-1400x-speedup-with-wideanddeep/ • Reduced pCTR model training from 75 hours/epoch on 450M samples to under 1 hour on 2B samples. • Built ArrowStreamServer, an in‑house low‑latency Parquet streaming library, repla https://cluster-site.onrender.com/posts/data-pipeline-challenges-of-privacy-preserving-federated-learning/ Thu, 05 Dec 2024 12:00:00 +0000 https://cluster-site.onrender.com/posts/data-pipeline-challenges-of-privacy-preserving-federated-learning/ • PPFL hides raw data from training org, preventing quality assessment and format validation. • Traditional preprocessing steps are often omitted in PPFL research, focusing solely https://cluster-site.onrender.com/posts/machine-learning-in-content-moderation-at-etsy/ Tue, 06 Aug 2024 11:15:03 +0000 https://cluster-site.onrender.com/posts/machine-learning-in-content-moderation-at-etsy/ • Etsy uses supervised ML to detect policy violations across 100M items. • Trust & Safety team combines community reports with automated removal. • Over 100,000 violations flagged https://cluster-site.onrender.com/posts/from-image-classification-to-multitask-modeling-building-etsys-search-by-image-feature/ Fri, 26 May 2023 20:32:49 +0000 https://cluster-site.onrender.com/posts/from-image-classification-to-multitask-modeling-building-etsys-search-by-image-feature/ • Etsy launches image-based search on mobile, letting users find similar items via photos. • Feature uses machine‑learning embeddings to represent 100M+ listings in low‑dimensional https://cluster-site.onrender.com/posts/modeling-sequences-with-quantum-states/ Thu, 16 Mar 2023 03:18:37 +0000 https://cluster-site.onrender.com/posts/modeling-sequences-with-quantum-states/ • Introduces quantum-inspired methods for modeling sequential data via tensor networks. • Uses bipartite graph representations of matrices to visualize linear maps. • Applies quant https://cluster-site.onrender.com/posts/understanding-entanglement-with-svd/ Thu, 16 Mar 2023 03:18:37 +0000 https://cluster-site.onrender.com/posts/understanding-entanglement-with-svd/ • SVD decomposes any matrix M into UDV†, revealing singular values and vectors. • Singular values, arranged in D, indicate the importance of each concept in M. • Left and right sin