Computer Vision Course with Real-Life Cases: Austin
December 2, 2019 @ 9:00 am - December 4, 2019 @ 6:00 pm
Already familiar with classic machine learning and now ready to move to the next step? The Practical Computer Vision course will provide you with practical means of solving business-specific tasks. During this course, attendees will proceed from theory to expert-led hands-on practice that encompasses a set of real-life use cases. In addition, you can submit a use case of choice to develop the expertise needed for your current business concerns.
- Find out how powerful some of the machine learning techniques might be;
- Explore the mechanisms for learning neural networks means of neural network learning process management;
- Learn how convolutional neural networks enhance machine learning for spatial data processing;
- Get familiar with the architectures that solve basic computer vision tasks;
- Get a sample code for training your own models to fit the needs of the business.
- Each trainee will have 16 hours of online Computer Vision practice with a personal trainer on the project of your choice.
Who should attend
- Everyone willing to improve knowledge and learn how to resolve issues challenging for classic machine learning;
- Engineers who want to gain practical expertise in computer vision and apply it to real-life business tasks.
Intro to Deep Learning
Explanation of a machine learning technique that are proven to be surprisingly powerful for a wide margin of tasks. We’ll look at a surprisingly strong machine learning techniques that have become really popular recently and will cover the following topics:
Convolutional Neural Networks
Neural network architecture for image processing. Successes of convolutional neural networks was the reason of a new wave of interest in machine learning. Convolution as the core of the neural network layer for spatial data processing. Topics for the day:
Computer vision drastically changed after the introduction of neural networks. In this module we’ll try to cover a basic tasks of computer vision using neural networks. During the lectures we’ll cover the architectures that solve the basic of the Computer Vision tasks and cover the following topics:
|Prediction on photo data set|
We will learn how to build models for detecting objects on images. Using satellite images, we’ll create a model to detect: trace segmentation, roadmap mining, ship detection.
Prediction on video data set
|In this task, video material will be used to build the model. Based on a set of video clips from fishing vessels, we’ll create a fish detection model.|
Your own project
|Each trainee can propose a project they’d like to work on.|
Altoros recommends that all students have:
- Programming: Basic Python programming skills, a capability to work effectively with data structures
- Experience with the Jupyter Notebook applications
- Basic experience with Git
- A basic understanding matrix vector operations and notation
- A basic knowledge of statistics
- Basic command line operations
All code will be written in Python with the use of the following libraries:
- Pandas/NumPy are the libraries for matrix calculations and data frame operations. We strongly recommend to browse through the available tutorials for these packages, for instance, the official one
A workstation with the following capabilities:
- A web browser (Chrome/Firefox)
- Internet connection
- A firewall allowing outgoing connections on TCP ports 80 and 443
The following developer utilities should be installed:
- Jupyter Notebook (will be installed using Anaconda)
All these libraries will be installed using Anaconda
If software requirements cannot be satisfied due to the security policy of your employer, please inform us about the situation to find an appropriate solution for this issue.
Vladimir has 10+ years of experience in software development. Over the course of his career, he has been part of 15 successful project implementations. Vladimir specializes in artificial intelligence and machine learning, distributed systems design, NoSQL and Hadoop-based systems benchmarking, permissioned blockchains, data engineering, and development of data-centric apps. As an expert in NoSQL databases, he has authored a number of research papers, comparing the performance of Apache Cassandra, Redis, MongoDB, and Couchbase. Vladimir also serves as a trainer and a data evangelist. He is responsible for analyzing requirements, preparing training materials, and conducting training sessions. Vladimir is an active member of the Open Data Science Community.
Kanstantsin is a Data Scientist who strives to solve business problems with a defined plan at all stages of the development process. He has considerable hands-on experience in using Machine Learning and statistical methods in various domains as well as solving business problems starting from problem definition up to model fine-tuning and solution deployment. He is profoundly knowledgeable about current trends and approaches to Machine Learning. Kanstantsin works with popular frameworks and packages in both R (tidyverse + caret) and Python (pandas/numpy + scikit-learn). He constantly follows the latest trends in Machine Learning and never stops investigating new techniques and technologies to expand his skill set.
! Please note the training is contingent upon having 5 attendees.
You can request private training for your team in your city and/or in your company, and we’ll do our best to make it happen. Fill in the form below and we’ll contact you once a training is scheduled in your desired location.