Search Results for "labeling"

...The project provides a large collection of tools that implement techniques from academic research on financial machine learning. It covers the full lifecycle of developing data-driven trading strategies, including data preprocessing, feature engineering, labeling techniques, model training, and performance evaluation. Many of the algorithms implemented in the library are based on concepts introduced in advanced quantitative finance literature and peer-reviewed research. The library also includes tools for constructing specialized financial data structures, generating predictive features, and evaluating trading strategies through backtesting. ...

Papers is a curated collection of concise summaries of machine learning research papers. The repository focuses heavily on deep learning, computer vision, reinforcement learning, generative models, and related fields. Summaries are organized into neural-network and mixed-topic directories for easier browsing. Individual entries condense key ideas from research papers so readers can review methods more quickly than reading each publication in full. Topic labels cover areas such as object...

The Janelia Automatic Animal Behavior Annotator (JAABA) is a machine learning-based system that enables researchers to automatically compute interpretable, quantitative statistics describing video of behaving animals. Through our system, users encode their intuition about the structure of behavior by labeling the behavior of the animal, e.g. walking, grooming, or following, in a small set of video frames. JAABA uses machine learning techniques to convert these manual labels into behavior detectors that can then be used to automatically classify the behaviors of animals in large data sets with high throughput. JAABA combines an intuitive graphical user interface, a fast and powerful machine learning algorithm, and visualizations of the classifier into an interactive, usable system for creating automatic behavior detectors. ...

Featurama is a library that implements various sequence-labeling algorithms. Currently Michael Collins' averaged perceptron algorithm is fully implemented.