This talk provides an introduction to the fundamentals of simultaneous localization and mapping (SLAM). We aim to provide foundational knowledge, and attendees are not expected to have any prerequisite experience in the field. The talk consists of an introduction to […]
In the real world, machine learning models are components of a broader software application or system. In this talk, Danielle Dean of iRobot will explore the importance of optimizing the system as a whole–not just optimizing individual ML models. Based […]
In this talk, we introduce the fundamentals of deep learning for image understanding. We begin by explaining the basics of convolutional neural networks (CNNs), and showing how CNNs are used to perform image classification and object detection. We provide an […]
Selecting the right imager and lens for your vision application is often a daunting challenge due to the vast number of products on the market and the large technical and performance differences between different product lines and technologies. In this […]
Camera systems used for computer vision at the edge are smarter than ever, but when they perceive the world in 2D, they remain limited for many applications because they lack information about the third dimension: depth. Sensing technologies that capture […]
We commonly train deep neural networks (DNNs) on existing data and then use the trained model to make predictions on new data. Once trained, these predictive models approximate a static mapping function from their input onto their predicted output. However, […]
Successful training of deep neural networks requires the right amounts and types of annotated training data. Collecting, curating and labeling this data is typically one of the most time-consuming aspects of developing a deep-learning-based solution. In this talk, we discuss […]
Embedding real-time large-scale deep learning vision applications at the edge is challenging due to their huge computational, memory, and bandwidth requirements. System architects can mitigate these demands by modifying deep-neural networks to make them more energy efficient and less demanding […]
In many modern vision and graphics applications, deep neural networks (DNNs) enable state-of-the-art performance for tasks like image classification, object detection and segmentation, quality enhancement and even new content generation. In this talk, we will demystify basic concepts behind DNN […]
In scientific papers, computer vision models are usually evaluated on well-defined training and test datasets. In practice, however, collecting high-quality data that accurately represents the real world is a challenging problem. Developing models using a non-representative dataset will give high […]
