Data Weekends™ are accelerated workshop for programmers where you can quickly learn to apply the most recent techniques to real-world data. We offer courses in Machine Learning and Deep Learning.
Our InstructorS: Francesco Mosconi
Francesco is CEO and Chief Data Scientist at Catalit Data Science. He is the author of the 5-day Zero to Deep Learning Bootcamp and book and founder of Data Weekends. Francesco works at the cutting edge of Machine and Deep Learning training, helping Fortune 500 companies to up-skill through intensive training programs and strategic advisory. Before Data Weekends, Francesco served as lead instructor in Data Science at General Assembly and The Data Incubator and he was Chief Data Officer and co-founder at Spire, a YCombinator-backed startup that invented the first consumer wearable device capable of continuously tracking respiration and activity. He earned a joint PhD in biophysics at University of Padua and Université de Paris VI.
WHO SHOULD TAKE THIS COURSE?
Software Engineers and Analysts with previous coding experience in Python
People who are interested in learning more about data analysis in Python
Coders who are curious about machine learning, text processing, and prediction.
All our courses offer a well balanced mix of 50% theory and 50% hands-on practice with the following activities:
Individual mentorship, feedback and support
Hands-on coding labs
Build a prototype from start to finish
Meet and learn with like-minded people
Case studies on real-world data and industry examples
Network of recruiting partners
A Data Science consultancy doing what we love: helping companies and individuals acquire skills and knowledge in the field of data science and harness the power of machine and deep learning to reach their goals.
We offer strategic and technical consulting across various domains related to data science, data analysis, information processing and machine learning. Please visit our website for more information: Catalit Data Science Consulting
Zero to Deep Learning® 5-day Bootcamp
A 1 week full-time training that brings you from Zero to Deep Learning® with Python, Pandas, Scikit-Learn, Keras and Tensorflow. It balances breadth and depth, and delivers you an immersive full-time introduction to cutting-edge ML and DL techniques. The course is designed for Software Engineers, Software Engineering Managers, and Data Analysts seeking to upskill in Machine Learning & Deep Learning.
Deep Learning Refresher with Keras and Tensorflow 1-day workshop
This course provides a refresher of how to use Keras and Tensorflow to build Deep Learning models. It provides examples and tools to use deep learning models on real world data. In this course you will learn about Fully Connected, Convolutional and Recurrent Neural networks and you will build models that work with images, text and numerical data.
Deploy Neural Networks to iOS using Keras and CoreML 1-day workshop
Learn to train a Neural Network that recognizes images of everyday objects and then you will deploy it to an iOS device (mobile phone or tablet).
Deploy Neural Networks to Android using Keras and TFLite 1-day workshop
Learn to train a Neural Network that recognizes images of everyday objects and then you will deploy it to an Android device (mobile phone or tablet).
Pytorch 1.0 for Keras developers 1-day workshop
Learn to design, train and debug Neural Networks using Pytorch 1.0
Advanced Deep Learning 3 day bundle
Bundle of 3 advanced 1 day workshops.
Refresher to Advanced Deep Learning 4 day bundle
Bundle of 1 day refresher and 3 advanced 1 day workshops.
For companies that want to run a course for their team we offer additional content and customized programs. These courses are offered through our parent company CATALIT LLC.
Data Analytics with Python, SQL and Spark
For people who are getting started with data analytics and want to analyze small and large datasets. In this course you learn to process structured and unstructured data, extract meaningful insights and visualize them. The course is a great starting point for the more advanced courses in machine learning and deep learning.
Machine Learning with Python, Pandas & Scikit-Learn
For people starting out with machine learning and looking to speed up their learning curve. This course provides a solid structure to organize your learning as well as code snippets and best practices. In this course you will learn to how to building, train and deploy machine learning models to predict continuous and discrete quantities.
INTRO TO DEEP LEARNING WITH PYTHON & KERAS
For people who already have a good understanding of machine learning and want quickly add deep learning to their toolbox. This course builds on top of the machine learning course providing examples and tools to use deep learning models on real world data. In this course you will learn about Fully Connected, Convolutional and Recurrent Neural networks and you will build models that work with images, text and numerical data
Advanced Deep Learning with Python & Tensorflow
For people who are already familiar with the fundamentals of machine learning and deep learning. Building on the basic and intermediate courses you will explore more advanced topics. In this course you will learn to use Tensorflow to train supervised deep learning models and you will discuss advanced topics like custom losses, model serving and transfer learning. You will review case studies from public repositories and discuss industry applications of deep learning at scale.
Reinforcement Learning with Python, Tensorflow & OpenAI
For people who are familiar with supervised deep learning and want to venture into unsupervised territory. In this course you will learn all about Q-Learning, Autoencoders and Adversarial Networks. You will train agents to play video games and apply unsupervised learning to a variety of problems.
WHAT MAKES US DIFFERENT?
We focus on Machine Learning and Deep Learning with Python.
Our courses are self-contained and hands-on. You get to the core of the matter and learn enough foundations to bypass the painful part of approaching a new subject. Your learning curve will go from months to days.
Whether you are considering moving a career move, or simply want to include predictive modeling in your work, our workshops give you the tools to do so.
In the last 2 years Python has become a de-facto standard in data science and it is widely adopted by most major companies. Reasons for this success include:
large set of mature data science libraries => most needs covered
worldwide community of enthusiasts => get help when you need it
easy to learn, read and write => start contributing immediately
supports both functional and object oriented coding => versatile and powerful
full stack programming language => easier interaction between data scientists and software engineers
Keras is a high-level neural networks api and library that allows to simply build and train deep learning models using Tensorflow or Theano as backend. Written in Python it focuses on enabling fast experimentation. It recently became the preferred high level api for Tensorflow and it thus provides a great entry point to approach Tensorflow. Keras highlights:
Allows for easy and fast prototyping
Supports Fully connected, Convolutional and Recurrent..
Supports arbitrary connectivity schemes
Runs seamlessly on CPU and GPU
Integrates very well with Tensorflow and Tensorboard
There are many open source Deep Learning libraries. Tensorflow is backed by Google and is quickly becoming one of the most used libraries in the fields. It has a large and growing community of users and it is versatile and easy to learn. Highlights include
largest community of developers
state of the art models and nodes
high scalability, can be distributed on many GPUs
production performance and deployment tools
very versatile and powerful for distributed high performance computing beyond neural networks
Apache Spark has revolutionized how we build and deploy data pipelines for ETL, Visualization and Machine Learning. Reasons for this success include:
Flexible enough to run SQL-style queries, machine learning algorithms, and everything in between
Fast and scalable: efficient memory use => runs up to 100x faster than Hadoop
Supports data exploration and production workflows => same code that works on a laptop can be deployed to cloud-based computing clusters
Free and open-source