Applied AI Study Group 2020 / Winter

The second study group in our AI programs, Applied AI Study Group, in which we come together on Saturdays to hold discussions by following IBM’s Applied AI course under guidance of Ahmet Melek, was concluded right before we have taken precautions in line with the official statements due the novel coronavirus outbreak. The whole journey was once again a greatly productive one, full of fresh codes  -see them on Github-, and ideas brought to light by our guide Melek.

In this discussion-based program the participants, who were already familiar with deep learning techniques, gained hands-on experience with various deep learning frameworks such as Keras, TensorFlow, PyTorch, DeepLearning4J and Apache SystemM and their applications, which will help them build models bringing solution for the real-life problems.

Check out what we had been learning each week below:

First Week:

We worked on four 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 Classification with  CIFAR-10 dataset on Keras sequential API , using Convolutional Neural Networks.

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

First week’s assignment:

• Key Point Detection with Large-scale Multiview 3D Hand Pose dataset on Keras, using Convolutional Neural Networks.

We worked on Google Colab for each example.

Second Week:

We worked on three problems:

• NLP: Word Embeddings and latent space operations with a custom mini-dataset on Keras, using Fully-Connected Neural Networks.

• NLP: Text classification with SMS Spam Collection Dataset on Keras, using Fully-Connected Neural Networks.

• Sequential data preparation and time series forecasting with Federal Reserve Economic Data Crude Oil Prices Chart on Keras, using LSTM Networks.

Second week’s assignment:

• Text Generation with scraped dataset on Keras to be beneficial for using existing scraping tools and using them to scrape an NLP dataset from web.

We worked on Google Colab for each example.

Third Week:

We worked on five problems:

• Sequential data preparation and anomaly Detection with Bearing Data Center Seeded Fault Test dataset on Keras, using LSTM autoencoders.

• Solution of Homework-2 was shown. Data acquisition, gentle scraping. Concept of temperature on generative models.

• Converting Keras models to DL4J models. Converting DL4J models to Apache Spark models via SystemML. After that, making a classification with Iris dataset on Apache Spark using Fully-Connected Neural Networks. For this example, we worked on IBM Watson studio.

• Converting Keras models directly to Apache Spark  models via SystemML. After that, making anomaly detection using Bearing Data Center Seeded Fault Test dataset on Keras, using LSTM autoencoders.

• Briefly mentioned the Eigenface method which is a traditional machine learning method, and used it to make biometric identification and face reconstruction from face encodings, on ORL dataset.
  

Also, we took a look at some further studies including real time data acquisition with IBM Node Red, cloud computing, edge computing, distributed computing and making deep learning models work faster.

Third week’s assignment was:

• Text Generation with scraped dataset on Keras to make use of existing scraping tools, and using them to scrape an NLP dataset from web.

We worked on Google Colab for each example.

Fourth Week

We worked on three problems:

• Image Classification with CIFAR-10 dataset on Pytorch, using Convolutional Neural Networks.

• Exploratory data analysis such as plotting, drawing charts, analyzing on Kaggle Wine Dataset, ULB Credit Card Fraud Detection Dataset and UCI Heart Disease Dataset.

• Structured Data Classification with the above-mentioned datasets, using traditional machine learning methods such as Logistic Regression, KNN, SVM, Bayesian Methods, Decision Trees, PCA, LDA, Bootstrap Aggregating Methods and Gradient Boosting Methods.
  

A  BEV Foundation project inzva is a non-profit hacker community organizing study and project groups as well as camps in the fields of AI and Algorithm; and gathering CS students, academics and professionals in Turkey.

Subscribe to our newsletter here and stay tuned for more hacker-driven activities by following us on our social media accounts to have the most recent news about our upcoming events and programs!