Results for “signal-processing”

Processes and analyzes multiple physiological signals (ECG, respiration, EDA, EMG, PPG, EOG) together using NeuroKit2, including cross-signal features like RSA and event-related analysis.

Foundational theory for process-oriented concurrency through synchronous message-passing, applicable to multi-agent coordination and parallel decomposition

Guides analysis of Neuropixels recordings from raw data to curated units, covering preprocessing, motion correction, spike sorting, quality metrics, and export.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Extract features from 1D signals using signalTimeFeatureExtractor, signalFrequencyFeatureExtractor, and signalTimeFrequencyFeatureExtractor. Use when computing time-domain features (amplitude, energy, shape factors), frequency-domain features (spectral location, power, bandwidth, PSD), or time-frequency features (spectral shape, instantaneous, ridges, wavelet, EMD-derived) on a per-frame basis. Use when the user asks to "extract features", "compute spectral features", "build a feature table for a classifier", "get per-frame statistics", "run feature extraction on this signal", or describes a vibration / biosignal / radar / sensor signal needing features for downstream ML or analysis. Includes optional GPU acceleration via canUseGPU and gpuArray. Does not cover filter design, audio-specific feature extraction (use audioFeatureExtractor in Audio Toolbox instead), batch dataset orchestration, or 2D / image features.

Designs and implements big data architectures, processes large-scale datasets with distributed systems, and optimizes data pipelines for throughput using Hadoop, Spark, and cloud platforms.

Process large-scale ML datasets with distributed streaming execution across CPU/GPU, supporting Parquet, CSV, JSON, images, and integration with PyTorch, TensorFlow, and Ray Train.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Aggregate and rank signals from multiple edge-finding skills into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection.

Classifies situations into 256 binary states and maps each to a prescribed action, reporting the pattern, decimal, name, range, and action to execute.

Generates spectrograms and multi-panel audio feature visualizations from audio files via a command-line tool.

Evaluates machine learning classifiers on their ability to distinguish signal from background in particle physics simulations, measuring how well algorithms rank signal events above background ones using the AUC metric.

Optimize prompts via process goals (controllable behavioral instructions) rather than outcome goals (sparse end-result demands). Grounded in sports psychology meta-analysis showing process goals (d=1.36) vastly outperform outcome goals (d=0.09). Use when designing prompts, optimizing LLM steering, implementing CoT/decomposition patterns, or building automatic prompt optimization pipelines. Instantiates surrogate loss paradigm for discrete prompt space.