Displaying 1 to 11 from 11 results

MachineLearningSamples-BiomedicalEntityExtraction - MachineLearningSamples-BiomedicalEntityExtraction

  •    Python

This real-world scenario focuses on how a large amount of unstructured unlabeled data corpus such as PubMed article abstracts can be analyzed to train a domain-specific word embedding model. Then the output embeddings are considered as automatically generated features to train a neural entity extraction model using Keras with TensorFlow deep learning framework as backend and a small amoht of labeled data.The detailed documentation for this scenario including the step-by-step walk-through: https://review.docs.microsoft.com/en-us/azure/machine-learning/preview/scenario-tdsp-biomedical-recognition.

babble-rnn - babble-rnn is a research project in the use of machine learning to generate new speech by modelling human speech audio, without any intermediate text or word representations

  •    Jupyter

babble-rnn is a research project in the use of machine learning to generate new speech by modelling human speech audio, without any intermediate text or word representations. The idea is to learn to speak through imitation, much like a baby might. The goal is to generate a babbling audio output that emulates the speech patterns of the original speaker, ideally incorporating real words into the output. The implementation is based on Keras / Theano, generating an LSTM RNN; and Codec 2, an open source speech audio compression algorithm. The resulting models have learned the most common audio sequences of a 'performer', and can generate a probable babbling audio sequence when provided a seed sequence.

LSTM-Text-Generation - Tons of fun with text and recurrent neural networks! Let your computer read a book and tell you its own story

  •    Hy

During the time that I was writing my bachelor's thesis Sequence-to-Sequence Learning of Financial Time Series in Algorithmic Trading (in which I used LSTM-based RNNs for modeling the thesis problem), I became interested in natural language processing. After reading Andrej Karpathy's blog post titled The Unreasonable Effectiveness of Recurrent Neural Networks, I decided to give text generation using LSTMs for NLP a go. Although slightly trivial, the project still comprises an interesting program and demo, and gives really interesting (and sometimes very funny) results. I implemented the program over the course of a weekend in Hy (a LISP built on top of Python) using Keras and TensorFlow. You can train the model on any text sources you like. Remember to give it enough time to go over at least fifty epochs, otherwise the generated text will not be very interesting, rather seemingly random garbage.

diluvian - Flood filling networks for segmenting electron microscopy of neural tissue

  •    Python

Flood filling networks for segmenting electron microscopy of neural tissue. Diluvian is an implementation and extension of the flood-filling network (FFN) algorithm first described in [Januszewski2016]. Flood-filling works by starting at a seed location known to lie inside a region of interest, using a convolutional network to predict the extent of the region within a small field of view around that seed location, and queuing up new field of view locations along the boundary of the current field of view that are confidently inside the region. This process is repeated until the region has been fully explored.

ResNetCAM-keras - Keras implementation of a ResNet-CAM model

  •    Python

The original Matlab implementation and paper (for AlexNet, GoogLeNet, and VGG16) can be found here. A Keras implementation of VGG-CAM can be found here. This implementation is written in Keras and uses ResNet-50, which was not explored in the original paper.


  •    CSharp

Keras.NET is a high-level neural networks API, written in C# with Python Binding and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research. Allows for easy and fast prototyping (through user friendliness, modularity, and extensibility). Supports both convolutional networks and recurrent networks, as well as combinations of the two. Runs seamlessly on CPU and GPU.