Conference about Big Data, High Load, Data Science, Machine Learning & AI
Machine Learning from Idea to Production
Bringing a machine learning model to production is a complex task involving many steps and technologies.
This talk proposes a sequence of steps you can use as a blueprint for your own project to give you maximum guidance to go to production quickly. These steps include checking / cleaning the data, getting an intuition for the data by plotting it, creating a base line for your model to see if it really performs well, feature selection, validate the model for over- and underfitting, and fine tuning the parameters of your model.
We will use Jupyter Notebooks, Pandas, matplotlib, Sklearn, Keras, and Tensorflow for this.
Introduction to Deep Learning with TensorFlow
Deep Learning is a special and most promising variant of Supervised Machine Learning. Most recent break-throughs have been fueled by instead of programming a system, you instead use known data to train a system, like you do in deep learning. We will touch classic Neural Networks, Convolutional Neural Networks (CNNs) for image processing, and Recurrent Neural Networks (RNNs) for processing of texts and other sequences.
We will use TensorFlow with Keras-style Layers and provide notebooks hosted on Google’s Colab, that allow them to run on GPU. Thus there will be no need for any installation, all you need is a browser. We will use Python as our language, but you do not need any knowledge of it. Knowledge of any Object oriented language is sufficient.