Both sides previous revisionPrevious revisionNext revision | Previous revision |
kb:ai [2018/11/17 19:40] – yehuda | kb:ai [2023/04/03 07:01] (current) – [NLP] yehuda |
---|
====== AI ====== | ====== AI / ML - Machine learning ====== |
ML / Machine learning | https://jalammar.github.io/visualizing-pandas-pivoting-and-reshaping/ |
| https://stanford-cs329s.github.io/syllabus.html |
| ===== NLP ===== |
| * https://allennlp.org/ |
| * https://github.com/facebookresearch/PyText |
| * https://github.com/NNLP-IL/Resources#named-entity-recognition-ner |
| |
| ===== AutoML ===== |
| |
| * [[https://github.com/AxeldeRomblay/MLBox|MLBox]] |
| * [[https://github.com/salesforce/TransmogrifAI|TransmogrifAI]] |
| * [[http://docs.h2o.ai/h2o/latest-stable/h2o-docs/automl.html|h2o automl]] |
| * [[https://github.com/jhfjhfj1/autokeras|autokeras]] |
| * [[http://epistasislab.github.io/tpot/|tpot]] |
| * https://www.automl.org/automl/ |
| |
| ===== Serving Engines ===== |
| * [[https://predictionio.apache.org/community/projects/#demos|predictionio]] |
| * [[https://github.com/combust/mleap/|MLeap]] |
| * [[https://www.h2o.ai/products/h2o-sparkling-water/|h2o-sparkling-water]] |
| |
| |
| ==== ML Serving engines / ML Scoring engine description ==== |
| === MLeap === |
| ככל הנראה שהעיקר מוטיבציה זה ליצור BUNDEL אחיד בנושא |
| |
| נתונים: |
| |
| ישנה סיריאליזציה של נתונים של ML PIPELINE |
| יש DOCKER ל SERVING |
| |
| חסורון : |
| |
| תחזוקתי שלא עושה WARM UP למודול (יתכן שישפיע על הביצועים) |
| |
| יתרון: |
| |
| התנהלות REST |
| |
| ===== formats ===== |
| |
| * [[http://dmg.org/pfa/docs/exoplanets/|pfa]] |
| * [[https://openscoring.io/|PMML]] |
| * MLeap |
| * Spark |
| |
| |
| |
| ===== speech recognition ===== |
| * https://cmusphinx.github.io/ |
| |
| |
| ==== Links ==== |
| |
https://keras.io/ | https://keras.io/ |
[[https://dzone.com/articles/11-open-source-frameworks-for-ai-and-machine-learn?edition=371223|AI ML - top 11 open source fw]] | [[https://dzone.com/articles/11-open-source-frameworks-for-ai-and-machine-learn?edition=371223|AI ML - top 11 open source fw]] |
| |
| [[https://www.seldon.io|seldon]] - seldon core - Open source platform for deploying machine learning models on Kubernetes |
| |
[[http://maxpumperla.com/elephas/|elephas - Deep learning on Spark with Keras]] | [[http://maxpumperla.com/elephas/|elephas - Deep learning on Spark with Keras]] |
| |
[[https://developer.nvidia.com/tensorrt|NVIDIA TensorRT]] - NVIDIA TensorRT™ is a platform for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications. TensorRT-based applications perform up to 40x faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and finally deploy to hyperscale data centers, embedded, or automotive product platforms. | [[https://developer.nvidia.com/tensorrt|NVIDIA TensorRT]] - NVIDIA TensorRT™ is a platform for high-performance deep learning inference. It includes a deep learning inference optimizer and runtime that delivers low latency and high-throughput for deep learning inference applications. TensorRT-based applications perform up to 40x faster than CPU-only platforms during inference. With TensorRT, you can optimize neural network models trained in all major frameworks, calibrate for lower precision with high accuracy, and finally deploy to hyperscale data centers, embedded, or automotive product platforms. |
| |
| [[https://caffe2.ai/|caffe2]] A New Lightweight, Modular, and Scalable Deep Learning Framework |
| |