Skip to content

Latest commit

 

History

History
64 lines (29 loc) · 2.61 KB

README.md

File metadata and controls

64 lines (29 loc) · 2.61 KB
Raw

Applied-AI-Study-Group

This is the repository for the content of inzva 2019-July Applied AI Study Group, guided by Ahmet Melek.

In the group we have worked on these subjects:

  • Frameworks: Tensorflow, Keras, SystemML, DL4J, Apache Spark

  • Problems: Image Classification, Image Generation (Image Restoration/Inpainting), Anomaly Detection, Timeseries Future Prediction, NLP Embedding, NLP Sentence Sentiment Classification

  • Architectures - Methods: Multilayer Perceptron (Fully-Connected Neural Networks), Convolutional Neural Networks (CNN), Long-Short Term Memory (LSTM), Autoencoders, Embedding Layers

  • Environments: Google Colab, IBM Watson Studio, Jupyter Notebook (Local)

Weekly Summaries

Week1

We have worked on three problems:

  • Image Classification with MNIST dataset on tensorflow, using Fully-Connected Neural Networks.

  • Image Classification with MNIST dataset on keras, using Convolutional Neural Networks.

  • Image Generation with aligned UTK dataset on keras, using Deep Convolutional Generative Adverserial Networks (DCGAN Autoencoder).

For all examples in Week1, we have worked on Google Colab.

Week2

We have worked on three problems:

  • Anomaly Detection with Bearing Data Center Seeded Fault Test dataset on keras, using LSTM autoencoders.

  • Timeseries future prediction with Federal Reserve Economic Data Crude Oil Prices Chart on keras, using LSTM Networks.

  • NLP Embedding and Classification with a custom mini-dataset on keras, using perceptrons, Fully-Connected Neural Networks and Embedding layers.

For all examples in Week2, we have worked on Google Colab.

Week3

We have worked on two problems:

  • Converting Keras models to DL4J models. Converting DL4J models to Apache Spark models via SystemML. After that, making classification with Iris dataset on Apache Spark using Fully-Connected Neural Networks. Worked on IBM watson studio.

  • Converting Keras models directly to Apache Spark models via SystemML. After that, making image generation with aligned UTK dataset on keras, using multilayer perceptrons. Worked on Google Colab. In this example, we have failed due to the complications with setting up Google Colab's environment.

Week4

We have worked on the solution of the project assignment which we had assigned in Week2.

Problem was detecting joint coordinates of a hand (knuckle coordinates), using images taken with webcams. We have assumed that the coordinates of the hand itself is already detected, and we have tried to predict the knuckle coordinates.

  • Trained with the "Large-scale Multiview 3D Hand Pose Dataset" by Rovit.

  • Used Convolutional Neural Networks on keras.