Machine Learning Bootcamp on Python- Predictive Analysis and Introduction of Neural Language Processing— DAY 1
Berlin, March 27-28th, 2019 instructed by Dr. Stylianos Kampakis
The purpose of this Bootcamp is to teach how to use Python and machine learning in order to learn predictive analysis of and recommender system. It takes you through all the steps, from collecting data using a web crawler to making profitable bets based on your predicted results.
- Intro to Python and Pandas.
- Instructions on how to build a crawler in Python for the purpose of getting stats.
- Data wrangling.
- Using machine learning for predictions.
Fundamentals of NLP
Intro to Spacy
Building a basic text classifier with scikit learn
What will you learn?
1) Design and code a machine learning pipeline in Python for predicting outcomes.
2) Build and use a web crawler in Python to extract the data from online sources.
3) Understand all the concepts and pitfalls of prediction analysis
Module 1: Introduction
Module 2: Python and Pandas primer
Module 3: Data crawling
Module 4: Model testing and metrics
Module 5: Data analysis
Machine Learning & Deep Learning Bootcamp-Recommender System— DAY 2
- What are recommendation engines
- How does a recommendation engine work?
- Data collection and Data storage
- Filtering the data
- Content-based filtering and Collaborative filtering
- The case study in Python using the public dataset
- Building a collaborative filtering model from scratch
- Building Simple popularity and collaborative filtering model
- Building a recommendation engine
- Evaluation metrics for recommendation engines
Module 1: Evaluating Recommender Systems
Module 2: A Recommender Engine Framework
Module 3: Content-Based Filtering
Module 4: Neighbourhood-Based Collaborative Filtering
Module 5: Matrix Factorization Methods
Module 6: Introduction to Deep Learning
Module 7: Deep Learning For Recommender Systems and scaling up
09:30 – 10:00 Registration
10:00 – 12:30 Masterclass
12:30 – 14:00 Lunch
14:00 – 17:30 Masterclass
17:30 – 18:00 Sponsor Talks
09:30 – 10:00 Registration
10:00 – 11:00 Intro to recommender systems
11:00 – 13:00 Machine Learning on Recommender System Lab
13:00 – 13:30 Questions TIme
13.30- 14.30 Lunch
14:30 – 15.30 Deep Learning on Recommender System
15:30 –17.00 Introduction to Deep Neural Networks and Keras
17:30 – 18:00 Questions Time
Who should attend?
- Data scientist who wants robust or learn more different applications
- Analyst: Companies who would like to offer re-education to their analytics team to their data science team or just upgrade yourself from analyst to data scientist.
- Developer, who wants to know more about the algorithm or even think about switching to be the data scientist
- Business Intelligence (BI): You are already familiar with statistics, want to understand better machine learning and prediction
What will participants need to know or do before starting this course?
This course is ideal for the analyst, junior data scientist, and BI also developer. A bit of knowledge of Python or machine learning will help you but it is not required. Have some familiarity with basic programming concepts or languages or statistics. Therefore, experience in Python or Machine Learning is not required but will help.
If you are not sure about your level, write us.
What does the price reflect?
The price reflects two things. First, it distills 7+ years of experience in a few hours, providing only the most relevant pieces for decision-makers, without all the jargon and the buzzwords. Secondly, it reflects the consultancy service which participants will get out of the workshop, and which is usually charged at much higher rates.
What are the problem-solving sessions about?
During the problem-solving sessions, we will solve on the blackboard any kind of problem the audience poses. In a previous workshop, for example, one of the problems was “How can we use Twitter data to predict Bitcoin prices?”. The solution included the full pipeline (from data collection to data storage), to actually solving the problem and hiring the right people. Feel free to contact me with your problems before the workshop date.
“Stylianos brings great enthusiasm to his workshop – his interest in all things AI shines through.” – Tim Gordon, Chief Executive at the Liberal Democrats
“Stylianos’s bespoke workshop allows for in-depth complicated analytical concepts to be understood in a manageable and easy way. Coving the background of the constant changing world of data science and breaking down the key concepts of data science.” – Dominik Byrne, Investor, Entrepreneur, Advisor
You can find more testimonials here.
P.S. The seats are limited to 12 people. We will send out the class materials as well as required library 2 weeks before the class, please follow the instruction and get the environment ready before coming to class.
¹ Dr. Stylianos Kampakis is an expert data scientist (with a decade of experience), member of the Royal Statistical Society, an honorary research fellow at the UCL Centre for Blockchain Technologies and startup consultant living and working in London. A natural polymath, with degrees in Psychology, Artificial Intelligence, Statistics, Economics and a PhD in Computer Science from University College London he loves using his broad skillset to solve difficult problems. You can learn more about his work at skampakis.com.