Format

100% online

Price

$10,728 

Duration

6 months, 20 hrs/wk

Cohorts start

Dec 10, 2020

Requirements

 1+ year of software engineering experience

Battle-Tested Machine Learning Models

We’ll teach you the most in-demand ML models and algorithms you’ll need to know to succeed as an Machine Learning Engineer. For each model, you will learn how it works conceptually first, then the applied mathematics necessary to implement it, and finally learn to test and train them.

Deep Learning 

Topics include: Overview of Neural Networks, backpropagation, and foundational techniques like stochastic gradient descent, Principles of Deep Neural Networks Common Deep Neural Network configurations e.g. RNNs, CNNs, MLPs, LSTMs, Generative Deep Learning and GANs, Linear algebra and calculus necessary for these models, Engineering Frameworks like Keras, TensorFlow, PyTorch, Fast.ai, and CuPy

The Machine Learning Engineering Stack

• Python Data Science Tools includes pandas, scikit-learn, Keras, TensorFlow 
• Machine learning engineering tools including Spark/PySpark, TensorFlow, Luigi, Docker, Hadoop, AWS, and Fast.ai 
• Software engineering tools including continuous integration, version control with Git, logging, testing, and debugging 

Computer Vision and Image Processing

• Foundations of computer vision and image processing including an introduction to OpenCV and how to use neural networks for image processing
• Image clustering and classification with K-means, multitask classifiers, and GANs 
• Object detection and image segmentation with techniques like Single Shot Detectors and YOLO Detection 
• Applications and trends in computer vision

ML Models At Scale and In Production

• Creating reliable and reproducible data pipelines to ensure your model is well fueled
• Cloud-based services provided by AWS, Microsoft Azure, and Google
• Using Dask and pandas to scale large datasets

Deploying ML Systems to Production

• Common tools and techniques to build large-scale AI applications
• Tools for building and deploying quality APIs like Swagger, Postman, FastAPI, and Paperspace 
• Productionizing models with CI and CD 
• Packaging your model into an interactive product like an app or website with tools like Streamlit, TensorFlow.js, and TensorFlow Lite
  

Working With Data

• Collecting data from APIs, RSSs, and web scraping chapter point Cleaning and transforming data for ML systems at scale, including tools for automatic transformation
• Working with large data sets in SQL and NoSQL database
• Tools like pandas, Spark, Dask, SQL, Spark SQL, and ScrappingHub

Start date

Dec 10, 2020

Tuition

$10,728