- 63

This is the implementation of the Variational Ladder Autoencoder. Training on this architecture with standard VAE disentangles high and low level features without using any other prior information or inductive bias. This has been successful on MNIST, SVHN, and CelebA. LSUN is a little difficult for VAE with pixel-wise reconstruction loss. However with another recently work we can generate sharp results on LSUN as well. This architecture serve as the baseline architecture for that model.

https://github.com/ermongroup/Variational-Ladder-AutoencoderTags | generative-model variational-inference unsupervised-learning feature-extraction representation-learning |

Implementation | Python |

License | Public |

Platform | Windows Linux |

Train Compositional Pattern Producing Network as a Generative Model, using Generative Adversarial Networks and Variational Autoencoder techniques to produce high resolution images. Run python train.py from the command line to train from scratch and experiment with different settings.

Welcome to my GitHub repo. I am a Data Scientist and I code in R, Python and Wolfram Mathematica. Here you will find some Machine Learning, Deep Learning, Natural Language Processing and Artificial Intelligence models I developed.

anomaly-detection deep-learning autoencoder keras keras-models denoising-autoencoders generative-adversarial-network glove keras-layer word2vec nlp natural-language-processing sentiment-analysis opencv segnet resnet-50 variational-autoencoder t-sne svm-classifier latent-dirichlet-allocationImplementation of the method described in our Arxiv paper. We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we replace element-wise errors with feature-wise errors to better capture the data distribution while offering invariance towards e.g. translation. We apply our method to images of faces and show that it outperforms VAEs with element-wise similarity measures in terms of visual fidelity. Moreover, we show that the method learns an embedding in which high-level abstract visual features (e.g. wearing glasses) can be modified using simple arithmetic.

Pyro is a universal probabilistic programming language (PPL) written in Python and supported by PyTorch on the backend. Pyro enables flexible and expressive deep probabilistic modeling, unifying the best of modern deep learning and Bayesian modeling.

pytorch machine-learning bayesian webppl inference probabilistic-programming probabilistic-graphical-models bayesian-inference variational-inference uberPyMC3 is a Python package for Bayesian statistical modeling and Probabilistic Machine Learning which focuses on advanced Markov chain Monte Carlo and variational fitting algorithms. Its flexibility and extensibility make it applicable to a large suite of problems.Note: Running pip install pymc will install PyMC 2.3, not PyMC3, from PyPI.

statistical-analysis bayesian-inference mcmc variational-inference theano probabilistic-programming bayesianThis is an implementation of Ladder Network in TensorFlow. Ladder network is a deep learning algorithm that combines supervised and unsupervised learning. It was introduced in the paper Semi-Supervised Learning with Ladder Network by A Rasmus, H Valpola, M Honkala, M Berglund, and T Raiko.

ladder-network deep-learning-algorithms unsupervised-learningIf you could successfully run the above demo, run following steps to train your own context encoder model for image inpainting. Features for context encoder trained with reconstruction loss.

image-inpainting context-encoders unsupervised-learning machine-learning generative-adversarial-network deep-learning computer-vision gan dcgan computer-graphicsCourse covers numerical optimization, statistical machine learning, Markov Chain Monte Carlo (MCMC), variational inference (VI) algorithms, data augmentation algorithms with applications for model fitting and techniques for dealing with missing data. Prerequisites: Bios 6341 (Fundamentals of Probability), Bios 6342 (Contemporary Statistical Inference), or permission of instructor. Students must be familiar with basic probability, have some formal programming experience, and be comfortable using the Git version control system.

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This generative model allows efficient search and optimization through open-ended spaces of chemical compounds. We train deep neural networks on hundreds of thousands of existing chemical structures to construct two coupled functions: an encoder and a decoder. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to the discrete representation from this latent space.

A composable GAN API and CLI. Built for developers, researchers, and artists. HyperGAN is currently in open beta.

gan supervised-learning unsupervised-learning learning generative-adversarial-network generative-model artificial-intelligence machine-learning machine-learning-api tensorflow classification generator discriminatorVIBES stands for Variational Inference in BayES Nets. It consists of a graphical Bayes Net editor and an inference engine which allows variational inference to be applied automatically using Variational Message Passing.

TensorFlow implementation of Learning from Simulated and Unsupervised Images through Adversarial Training. Result of lambda=1.0 with optimizer=sgd after 8,000 steps.

tensorflow synthetic-images deep-learning apple generative-modelLecture notes on Bayesian deep learning

deep-learning probability-theory variational-inferencePyTorch implementation of Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. * All samples in README.md are genearted by neural network except the first image for each row. * Network structure is slightly diffferent (here) from the author's code.

gan generative-model unsupervised-learning pytorchTensorflow implementation of Neural Variational Inference for Text Processing. Training details of NVDM. The best result can be achieved by onehost updates, not alternative updates.

The Deep Face Representation Experiment is based on Convolution Neural Network to learn a robust feature for face verification task. The popular deep learning framework caffe is used for training on face datasets such as CASIA-WebFace, VGG-Face and MS-Celeb-1M. And the feature extraction is realized by python code caffe_ftr.py. The single convolution net testing is evaluated on unsupervised setting only computing cosine similarity for lfw pairs.

face-recognition caffeOpenCog is a framework for developing AI systems, especially appropriate for integrative multi-algorithm systems, and artificial general intelligence systems. Though much work remains to be done, it currently contains a functional core framework, and a number of cognitive agents at varying levels of completion, some already displaying interesting and useful functionalities alone and in combination. With the exception of MOSES and the CogServer, all of the above are in active development, are half-baked, poorly documented, mis-designed, subject to experimentation, and generally in need of love an attention. This is where experimentation and integration are taking place, and, like any laboratory, things are a bit fluid and chaotic.

agi natural-language natural-language-inference natural-language-understanding robotics robot-controller learning learning-algorithm unsupervised-learning unsupervised-machine-learning unsupervised-learning-algorithmsCode for reproducing key results in the paper Improving Variational Inference with Inverse Autoregressive Flow by Diederik P. Kingma, Tim Salimans, Rafal Jozefowicz, Xi Chen, Ilya Sutskever, and Max Welling. Set floatX = float32 in the [global] section of Theano config (usually ~/.theanorc). Alternatively you could prepend THEANO_FLAGS=floatX=float32 to the python commands below.

The Natural Language Decathlon is a multitask challenge that spans ten tasks: question answering (SQuAD), machine translation (IWSLT), summarization (CNN/DM), natural language inference (MNLI), sentiment analysis (SST), semantic role labeling(QA‑SRL), zero-shot relation extraction (QA‑ZRE), goal-oriented dialogue (WOZ, semantic parsing (WikiSQL), and commonsense reasoning (MWSC). Each task is cast as question answering, which makes it possible to use our new Multitask Question Answering Network (MQAN). This model jointly learns all tasks in decaNLP without any task-specific modules or parameters in the multitask setting. For a more thorough introduction to decaNLP and the tasks, see the main website, our blog post, or the paper. While the research direction associated with this repository focused on multitask learning, the framework itself is designed in a way that should make single-task training, transfer learning, and zero-shot evaluation simple. Similarly, the paper focused on multitask learning as a form of question answering, but this framework can be easily adapted for different approached to single-task or multitask learning.

deep-learning natural-language-processing multitask-learningStanford Unsupervised Feature Learning and Deep Learning Tutorial

deep-learning deep-learning-tutorial convolutional-neural-networks
We have large collection of open source products. Follow the tags from
Tag Cloud >>

Open source products are scattered around the web. Please provide information
about the open source projects you own / you use.
**Add Projects.**