Join

Computer vision courses

186 Courses

California Institute of Technology

Introduction to artificial intelligence for trainers

Module 1: Fundamental Concepts in Artificial Intelligence (AI) and Machine Learning By the end of this module, you'll be able to: Distinguish between supervised, unsupervised, and reinforcement learning, and identify the type of machine learning most suitable for certain scenarios. Assess t.
California Institute of Technology

IBM Watson - Build Chatbot with IBM Watson

IBM Watson - Build Chatbot with IBM Watson IBM Watson - Build Chatbot with IBM Watson A beginners guide into the AI technology of IBM Watson. Learn to build and integrate your Chatbot using IBM Watson. Categories: Artificial Intelligence Courses, Machine Learning Courses, Computer Vision Courses, IBM Wa.
course image
California Institute of Technology Delft University of Technology

AI in Architectural Design

AI in Architectural Design Are you navigating through the maze of AI discussions in everyday conversations? Do you feel overwhelmed and find it challenging to keep up with the constant flow of AI news? Or perhaps you are enthusiastic about AI and its transformative power in design practices. This course will shed light on the science behind the.
course image
provider edX
pricing Free Online Course (Audit)
duration 4 weeks, 2-4 hours a week
sessions On-Demand
California Institute of Technology Coursera

Réseaux neuronaux et Deep Learning

Vous souhaitez vous lancer dans l’IA de pointe ? Ce cours est là pour vous y aider. Les ingénieurs en Deep Learning sont très convoités et la maîtrise de ce domaine vous ouvrira de nombreuses opportunités professionnelles. Le Deep Learning est également un nouveau « superpouvoir » qui vous permettra de développer des systèmes d’IA qui n’étaient.
course image
provider Coursera
pricing Free Online Course (Audit)
duration 20 hours
sessions On-Demand
California Institute of Technology AWS Skill Builder

Computer Vision with GluonCV (German)

In diesem Kurs erhalten Sie ein nützliches Verständnis der Komponenten eines konvolutionalen neuronalen Netzwerks (Convolutional Neural Network – CNN) wie Konvolutionen und Pooling-Ebenen usw. In diesem Kurs zeigen Alex Smola und Tong He, wie man einige Computer-Vision-Techniken mit GluonCV, einem Computer-Vision-Toolkit, implementiert. Hinweis.
course image
provider AWS Skill Builder
pricing Free Certificate
duration 2 hours
sessions On-Demand
California Institute of Technology AWS Skill Builder

Computer Vision with GluonCV (Japanese)

Computer Vision with GluonCV (Japanese) ＊このコースの中のビデオには日本語の字幕がついています。字幕を表示させるには、ビデオ画面下のアイコンをクリックしてください。 説明 このコースでは、畳み込みやプーリング層など、畳み込みニューラルネットワーク (CNN) のコンポーネントについての理解を深めます。このコースでは、Alex Smola と Tong He が、コンピュ.
course image
provider AWS Skill Builder
pricing Free Certificate
duration 2 hours
sessions On-Demand
California Institute of Technology AWS Skill Builder

Computer Vision with GluonCV (Portuguese)

Computer Vision com GluonCV (Portuguese) Neste curso, você obterá conhecimentos práticos sobre os componentes de uma rede neural convolucional (CNN), como convoluções, camadas de agrupamento etc. Alex Smola e Tong He mostram como implementar algumas técnicas de visão computacional usando o GluonCV, um toolkit de visão computacional. Observação: E.
course image
provider AWS Skill Builder
pricing Free Certificate
duration 2 hours
sessions On-Demand
California Institute of Technology AWS Skill Builder

Computer Vision with GluonCV (French)

Computer Vision with GluonCV (French) Dans ce cours, vous allez développer des connaissances utiles sur les composants d'un réseau neuronal convolutif comme les convolutions, les couches de pooling, etc. AlexSmola et TongHe expliquent comment implémenter certaines techniques de vision par ordinateur en utilisant GluonCV, une boîte à outils de vis.
course image
provider AWS Skill Builder
pricing Free Certificate
duration 2 hours
sessions On-Demand
California Institute of Technology edX

Vision artificielle et exploitation intelligente des ressources naturelles

Vision artificielle et exploitation intelligente des ressources naturelles Bienvenue au cours VIARENA, «Vision artificielle et exploitation intelligente des ressources naturelles». La vision artificielle est l'art et la science de rendre les ordinateurs capables d'interpréter intelligemment des images. Il existe une multitude d'applications de la.
course image
California Institute of Technology University of Colorado Boulder

컴퓨터 비전 분야에서의 딥 러닝 응용 사례

컴퓨터 비전 분야에서의 딥 러닝 응용 사례 이 강의는 CU 볼더 대학교의 데이터 과학 석사(MS-DS) 학위 과정의 일부로써 학점 인정이 가능하며 Coursera 플랫폼을 통해 제공됩니다. MS-DS는 CU 볼더 대학교의 응용 수학, 컴퓨터 과학, 정보 과학 및 기타 여러 학과 교수진이 모여 만든 학제간 학위 과정입니다. MS-DS는 능력에 따라 입학이 허가되고 지원 절차가 없기 때문에.
course image

“Computer vision student” sounds like a quote from science fiction, don’t you think? In fact, a computer vision engineer is a profession that, although it has not yet become the most widespread, is already rapidly gaining popularity and offers high salaries even at the start of a career.

What is computer vision and what does its developer do?

A computer vision engineer is a specialist who teaches computers to extract information from images. In particular, automatically recognize objects or gestures in images and videos. If a person can visually determine something (for example, find a defect in a product), a computer can also be trained to do this - and thus save time and resources, simplifying many processes.

Developments in the field of computer vision courses are used in a wide variety of companies whose products are related to images or video. This includes the production of self-driving cars, helping doctors interpret MRI images when searching for tumors, and even facial recognition in the subway to identify violators of the self-isolation regime. Computer vision specialists help many e-commerce businesses reduce the burden of moderation: for example, when an ad service like Avito fights trolls who upload pictures with inappropriate content.

Computer vision specialists after computer vision courses are called differently: developers, engineers, and researchers (computer vision scientist). Essentially, a computer vision specialist is more of an engineer who uses mathematics and programming as working tools. So, globally, a computer vision engineer, a computer vision scientist, a computer vision developer and a technical vision developer are one and the same thing.

What does a computer vision developer actually do?

As a rule, the day of such a specialist begins with a stand-up with the team. He then writes code to train neural networks, preprocesses data, and analyzes experiments. A computer vision developer can work alone or in a team, where everyone performs part of a larger task.

As for working tools, the Python language is usually used to write code for experiments, and the Tensorflow or Pytorch frameworks are used to train neural networks. The work also involves special libraries for image processing such as OpenCV. For high-load projects, the C++ language can also be used, since anything written in it is executed many times faster.

Computer vision is a young, dynamically developing field at the intersection of science and engineering, in which there are still more experiments than ready-made solutions. To grow, a specialist here needs to constantly learn. But it is the novelty and non-standard nature of the tasks, as well as the opportunity to create something truly innovative, that brings many people into this profession.

What do they teach in computer vision classes at AI Education?

Training at the best computer vision course typically consists of three modules: creating infrastructure, basics of machine learning and studying computer vision.

The first block at a computer vision online course can be called introductory. Since specialists in the field of computer vision rely on knowledge of mathematics and programming when solving problems, at the start they will have to study from scratch or brush up on topics from higher mathematics, mathematical analysis and linear algebra, as well as work with the Python language. Don’t worry if your knowledge is limited to school mathematics, which was “long ago and not true”: we will help you improve the necessary topics in the first module, so that in the future all students can move through the program at the same rhythm.

The second module is entirely devoted to machine learning. It helps solve computer vision problems faster and easier. For example, for facial recognition, you can expertly describe facial features based on questions that are asked when compiling an identikit. Or you can feed the algorithm a lot of photographic portraits with markings about which face belongs to whom, and then the algorithm itself will learn to extract features by which faces can be identified. In the future, if you need to determine who is in the photo, the algorithm will only need a database of portraits. If there is a photo of the person you need, the system itself will easily find him.

In the second module you will examine probability theory and mathematical statistics. Students will practice solving problems using fundamental algorithms and data structures in Python, become familiar with Python libraries for Data Science (NumPy, Matplotlib), as well as machine learning algorithms.

Finally, in the third module at this machine vision course you will analyze the main tasks of computer vision, we will work with mathematical morphology and the OpenCV and PIL libraries!