Jupyter hub and Binder

by Carol Wiling

Abstract - We'll take an in-depth look at JupyterLab and its use for data science and scientific computing. We'll look at the new user interface functionality available to users of JupyterLab. Later, we will move beyond an individual's workflow with JupyterLab and see how JupyterHub brings JupyterLab to groups of users. We'll wrap up with a discussion of Binder and its ability to provide ephemeral computing environments for Jupyter notebooks and beyond.

Understanding NLP - What's the feeling ?

By Lakshya Sivaramakrishnan (Google)

Abstract - This intermediate level talk would cover the basics required for natural language processing using NLTK in Python. We would then see it working in action through a sentiment analysis use-case.
Prerequisites - Basic knowledge of Python.

Programming a Quantum Computer using Cirq

by Vamsi Krishna Devabathini (Google)

Abstract - This intermediate level workshop will focus on introduction to quantum computing and Cirq, python framework for creating quantum programming. It also includes a hands on tutorials implementing simple quantum algorithm(s) using Cirq.
Prerequisites - Basic knowledge of Python. Knowledge of Quantum computing is a plus but not required.

Python ML On the Cloud

By Krishna Balaga (IBM)

Abstract - A no tricks under the sleeve session with pure python at its heart for understanding and Solving Machine Learning problems. This can be categorized as a beginner level workshop on how to get the basics right. We start with a problem statement and then proceed with obtaining the required dataset, getting it ready for our ML model, build and evaluate the model and finally we teach you how to host your ML model on the cloud so that it's just an API call away. By the end of the session, you will be able to scheme out a healthy approach to any harder set of machine learning problems.
Agenda -

1. Introduction to Machine Learning
   • AI vs ML vs DL
   • Supervised vs Unsupervised
   • Ml Algorithms and its use cases
2. Machine Learning Pipeline
   • Golden Rule of ML
   • Goals of Pre-processing
     • Handling missing data
     • Data Transformation
     • Outliers
     • Categorical Data
   • Feature Extraction
     • Co-relation of Features
     • Dimensionality Reduction
     • PCA
   • Model Training
     • Linear Regression
     • Decision Tree
     • Ensemble Models
     • Feedback and Deployment
3. Train a Logistic Regression Model (HANDS ON Lab)
   • Hands-on
   • Loading the data and connecting to Cloud Object Storage
   • Splitting the data, Feature Engineering and model fitment
4. Model Evaluation and improvisation
   • ROC Analysis
   • Hyper-Parameter Optimization
5. Exporting the Model as an API endpoint
   • Python notebook based code demonstration