arrow-next arrow-scroll arrow-short arrow check close dropdown facebook instagram linkedin search twitter

This course teaches you to deploy the workhorse of modern machine learning frameworks: neural networks. We start with the simplest building block, the perceptron, and demonstrate how these are organized into feed forward neural networks. We then explore predictive capabilities in computer vision, and time series analysis. Different architectures are employed for specific application areas.

This course includes:

  • Data Topics
    • Neural networks: the perceptron, feed forward neural networks
    • Computer vision: convolutional neural networks, importing and manipulating images, generating images
    • Time series analysis: long/short term memory networks, autocorrelation
  • Software Topics
    • Flask applications
  • Sessions
    • S1: Multilayer Perceptron
    • S2: Feed Forward Neural Networks
    • S3: Computer Vision I
    • S4: Computer Vision II
    • S5: Building Applications with Flask
    • S6: Time Series Analysis
    • S7: Data Dashboards with Plotly Dash
  • Labs
    • L1: Neural Network Linearity
    • L2: Wine Quality Prediction
    • L3: Motor Impeller Quality Prediction
    • L4: Customer Forecasting
    • L5: Motor Impeller Flask Application
  • Projects
    • P1: Monolithic Tic-Tac-Toe App
    • P2: Microservices Tic-Tac-Toe App
    • P3: Unit Tests for Flask Applications
    • P4: Continuous Integration for Flask Applications

By the end of this course, you will have demonstrated predictive capabilities in computer vision, forecasting, and time series analysis using neural networks.

 

 

 

 

Quick Facts

Dates:

Spring 5/16/2022 – 5/26/2022

Days: Monday – Thursday

Time: 5:00p.m. – 7:30p.m. PT

Format: Online instruction

      Cost: $1250

      Prerequisites: Python Foundations

      and DS Foundations or equivalent
      

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Meet the Instructor

Dr. Beckner is a GIX faculty member, an instructor for the University of Washington MS in Technology Innovation, a Data Science Advisor for the Pfaendtner Research Group, and partner at MFG Analytic, where he works with manufacturing clients to optimize their production processes using cloud-based tools. He received his Ph.D. in Chemical Engineering Data Science from the University of Washington and his B.S. in Chemical Engineering from the University of Texas at Austin. His consulting work inspired him to help organizations streamline their workflows and increase profit margins by training in-house employees to better understand and use data. Read his full biography here.

Instructor’s Take: As engineers or business professionals we will often have at our fingertips data that can lead to miraculous business value, but we don’t know how to leverage it. To make matters more difficult, bringing in an external data science team can have cost and time hurdles, as they are expensive and don’t understand the domain area. Coming out of this course you will have the ability to apply machine learning to the truly cutting-edge application areas of computer vision, and forecasting.

Getting a peek behind the curtain of Machine Learning, what it is, and how it actually works, was probably most valuable to me professionally of all the topics in these courses.

Matt, PAST PARTICIPANT

View Other Data Science for engineers Courses