Become a sponsor to Tomasz Latkowski
I am working on machine/deep learning projects related to different domains: natural language processing, natural language understanding, computer vision, recommender systems, medical databases. I have got an applied knowledge in implementation of various machine learning algorithms: feed-forward neural networks, convolutional neural networks, recurrent neural networks, neural attention mechanism, encoder-decoder architectures and generative adversarial networks. I have got a PhD application in Electronics field. My thesis concerned the analysis of subset of various feature selection algorithms in order to select the most significant attributes with solid distinctive abilities from medical databases.
Featured work
-
tlatkowski/inpainting-gmcnn-keras
Keras implementation of "Image Inpainting via Generative Multi-column Convolutional Neural Networks" paper published at NIPS 2018
Python 93 -
tlatkowski/deep-learning-gene-expression
Deep learning methods for feature selection in gene expression autism data.
Jupyter Notebook 34 -
tlatkowski/multihead-siamese-nets
Implementation of Siamese Neural Networks built upon multihead attention mechanism for text semantic similarity task.
Jupyter Notebook 183 -
tlatkowski/tf-feature-selection
Implementation of various feature selection methods using TensorFlow library.
Python 9 -
tlatkowski/neural-recommender
Neural recommender system implementation in TensorFlow.
Python 16 -
tlatkowski/gans-2.0
Generative Adversarial Networks in TensorFlow 2.0
Python 78
$25 a month
SelectCarrying on works on projects related to implementation of several feature selection algorithms in Tensorflow:
https://github.com/tlatkowski/tf-feature-selection
- Add a support of TensorFlow 2.0.
- Implementation of more advanced feature selection algorithms: ReleifF, Linear SVM, Kolmogorov-Smirnov test, Stepwise regression method.
$40 a month
SelectSupporting and maintaining Inpainting project related to computer vision (unofficial Keras implementation of approach proposed at NeurIPS 2018): https://github.com/tlatkowski/inpainting-gmcnn-keras
$50 a month
SelectCarrying on works on project related to natural language understanding and text semantic similarity: https://github.com/tlatkowski/multihead-siamese-nets
- Implementation of different models to compare with existing ones: ResNet, Capsules Net, Highway network.
- Implementation of char-based embeddings.
- Online demo application for model testing.
$100 a month
SelectCarrying on works on project Generative Adversarial Networks in TensorFlow 2.0:
https://github.com/tlatkowski/gans-2.0
- Implementation on more advanced GAN models: Wasserstein GAN, Cycle GAN and so on.
- Extension of dataset domains to music domain.
- Demo application for model testing.