COMPUTER VISION WORKSHOP
The Computer Vision Training Program Is Designed to Bring Your Team Up To Speed With Best Practice Implementation Skills
Computer Vision Training Workshop Overview
This 5-day intensive workshop prepares practitioners to apply deep learning techniques to computer vision problems, i.e., the automated analysis & interpretation of images. This includes the rudiments of computer vision theory & methods (e.g., feature extraction, object recognition, registration, segmentation, etc.) and principles of machine learning & deep learning (e.g., supervised/unsupervised learning, neural networks, etc.). The principal goal is to develop the core understanding to support building practical computer vision systems for tasks like object recognition in various realistic lighting conditions or natural settings.
We assume participants have undergraduate-level knowledge of mathematics (specifically calculus and linear algebra). They should also be comfortable using the Python language and, in particular, working with standard Python tools for data analysis & visualization (notably NumPy, Pandas, Jupyter, and Matplotlib). No prior experience using libraries for computer vision (e.g., OpenCV, etc.) or machine/deep learning (e.g., Scikit-Learn, PyTorch, TensorFlow, etc.) is expected.
At the conclusion of this course, participants will be able to:
●Articulate & apply standard computer vision concepts & terminology (e.g., filtering, convolution, registration, segmentation, etc.) in relevant application contexts.
●Implement standard image processing tasks (e.g., convolution, filtering, edge detection, etc.) either the hard way (e.g., NumPy) or with standard tested libraries (e.g., OpenCV).
●Articulate & apply fundamental machine learning terminology & concepts (e.g., supervised learning, regression, classification, unsupervised learning, clustering, dimensionality reduction, etc.) in image analysis or computer vision contexts.
●Construct from scratch working examples of neural networks with specified architectures of varying depth & complexity with a standard software framework in Python.
●Modify or tune the architecture of an existing computer vision pipeline based on deep learning models to meet specific performance optimization criteria.
●Identify practical constraints in computer vision application scenarios & choose appropriate technologies required for building production systems.