Chevron Left
返回到 Visual Recognition & Understanding

学生对 纽约州立大学布法罗分校 提供的 Visual Recognition & Understanding 的评价和反馈

课程概述

This course immerses learners in deep learning, preparing them to solve computer vision problems. Learners plunge into the field of computer vision that deals with recognizing, identifying and understanding visual information from visual data, whether the information is from a single image or video sequence. Topics include object detection, face detection and recognition (using Adaboost and Eigenfaces), and the progression of deep learning techniques (CNN, AlexNet, REsNet, and Generative Models.) This course is ideal for anyone curious about or interested in exploring the concepts of visual recognition and deep learning computer vision. Learners should have basic programming skills and experience (understanding of for loops, if/else statements), specifically in MATLAB (free introductory tutorial: https://www.mathworks.com/learn/tutorials/matlab-onramp.html). Learners should also be familiar with the following: basic linear algebra (matrix vector operations and notation), 3D co-ordinate systems and transformations, basic calculus (derivatives and integration) and basic probability (random variables). It is highly recommended that learners take the “Deep Learning Onramp” course available at https://matlabacademy.mathworks.com/. Material includes online lectures, videos, demos, hands-on exercises, project work, readings and discussions. Learners gain experience writing computer vision programs through online labs using MATLAB* and supporting toolboxes. This is the fourth course in the Computer Vision specialization that lays the groundwork necessary for designing sophisticated vision applications. To learn more about the specialization, check out a video overview at https://youtu.be/OfxVUSCPXd0. * A free license to install MATLAB for the duration of the course is available from MathWorks....
筛选依据:

1 - Visual Recognition & Understanding 的 7 个评论(共 7 个)

创建者 Nhon Q

Sep 18, 2019

Material not ready for prime time. More like a brief survey on the subject of Visual Recognition. One can finish this class in less than 3 hours.

创建者 Hongming Z

Jul 20, 2019

The first test answer is not formal enough. The answer can not let % and 0. ... as the right answer.

Good videos

创建者 Brice L

Aug 29, 2019

It is a bit better than the previous classes of this specialization but still not great. On the positive side, there is a lot of presentations of the visual recognition techniques and the classes relies on the Matlab tutorials to develop practical skills. On the negative side, like in the previous classes, the videos miss many parts so you will hear a lot from the trainer "let us see something" but nothing will show up.

创建者 Jose M G L

Oct 25, 2019

Good high level overview of NN and deep learning.

Very poor support (none) from teachers. Videos lacking the examples they refer to!

创建者 Juan l

Sep 24, 2019

Incomplete content

创建者 Alan T

Oct 29, 2019

I received full credit for an assignment even though I had only half the answers correct. I received the completion certificate upon completion of week 2, but I guess that's okay since there are no assignments in weeks 3 or 4. Video lectures are missing content.

创建者 Abdulaziz A

Oct 16, 2019

Pros: inspiring course.

cons:

Not satisfied .Not as I expected. No correlations between assignments and videos

Very short videos with no details explanation. As if he is summarizing news outlines.