H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
Fabric for Deep Learning (FfDL, pronounced fiddle) is a Deep Learning Platform offering TensorFlow, Caffe, PyTorch etc. as a Service on Kubernetes
An open source CUDA-C++ platform for accelerated deep learning inference
An Open Source, Self-Hosted Platform For Applied Deep Learning Development
An open source deep learning platform that provides a seamless path from research prototyping to production deployment
Neuralet is an open-source platform for edge deep learning models on edge TPU, Jetson Nano, and more.
Neuralet edge deep learning models library. Neuralet is an open-source platform for edge deep learning models on GPU, TPU, and more.
An open source implementation of the deep learning platform for undersampled MRI reconstruction described by Hyun et. al. (https://arxiv.org/pdf/1709.02576.pdf)
CustomerML is an open source customer science platform leveraging the power of Predictiveworks and fully integrated with Elasticsearch and Shopify. CustomerML starts with proven RFM analysis and combines the results with machine learning thereby providing a deep customer understanding.
The Deep Learning Seminar is for both graduate and undergraduate students that have special interests on Deep Learning (DL). In this seminar series, the students will collaborate in an intensive examination of topics related to understanding the basic concepts, models and algorithms of DL. The basic module of the Deep Learning seminar is designed as a discussion seminar. Emphasis will be on close reading and discussion of the assigned readings. Each volunteer participant will be responsible for leading the seminar discussion on assigned weeks. All participants are expected to come prepared to discuss and debate the readings each week. Participants will develop their understanding of the material through class presentations and discussions. An advanced module of source code review is designed for the participants that want to develop their skills on implementing existing DL models and designing new models. Emphasis will be on close review and discussion of the DL models. Each participant will be responsible for leading the seminar discussion on mathematic formulas, algorithms and the source code of the assigned model. In particular, this seminar will use Apache SINGA (http://singa.apache.org/), an open source DL platform for code review.