This is a short video of lecture about neural networks by Caltech. It covers essential concepts such as the construction of neural nework, the learning algorhtms, etc.
Type of Material:
Presentation
Recommended Uses:
In-class, lecture or self-paced uses.
Technical Requirements:
It can be viewed through most browsers.
Identify Major Learning Goals:
This is a video lecture on neural networks, allowing students to learn about the concept of neural networks. Stochastic gradient descent, neural network model and backpropogation algorithm are introduced.
Target Student Population:
Undergraduate and postgraduate students who want to learn the basic concept of neural networks.
Prerequisite Knowledge or Skills:
Students should have foundational knowledge in computing or computer science, including good mathematical skills. Elementary knowledge of problem formalization using mathematical modeling is needed, in particular, the basic skill of optimization is preferred.
Content Quality
Rating:
Strengths:
Very clear presentation by a good teacher. The pointer is good. It explains the concept well with diagrams. Information is generally sufficient.
Summary:
- The formulation of problems that to be applied in neural networks is introduced.
- It clearly presented the inspiration of biological function to neural network.
- The creation of layers in NN is also illustrated.
Concerns:
This is a longer lecture. It is better if it can be broken into sessions.
Potential Effectiveness as a Teaching Tool
Rating:
Strengths:
It is effective for learning the basic concept. The presentation is generally concise and clear. It can be integrated with a course on neural networks. In particular, students can be asked to see this video lecture before or after a class.
It is a lecture of a course. It contents the review of the previous course. The expected outcome of the lecture is clearly presented. When explaining the benefits of SGD, some relevant examples are introduced. The presenter is enthusiastic in the presentation as well as in answering questions.
Concerns:
- As a standalone content, viewers may need sometime to get used to the presentation approach, especially on the problem modelling.
- It uses quite substantial mathematical models and optimizations to explain the idea.
Ease of Use for Both Students and Faculty
Rating:
Strengths:
- It is good for self learning or viewing after class.
- The video synchronizes the presenter's action on stage with the slides being presented, so the viewers can be more engaged like sitting in the lecture room attending the lecture.
- Using examples of birds and aeroplane gives good inspiration on the idea of perceptrons.
- Contents are displayed clearly.
Concerns:
- As the video is over an hour, it limits the use in class.
- As it sometimes refers to some contents presented in the previous lectures. e.g. "movie rating", some viewers may get distracted as the background of the case is not reiterated.
- It is better if the lecture can be divided into sessions. Furthermore, some questions/exercises can be added.
Creative Commons:
Search by ISBN?
It looks like you have entered an ISBN number. Would you like to search using what you have
entered as an ISBN number?
Searching for Members?
You entered an email address. Would you like to search for members? Click Yes to continue. If no, materials will be displayed first. You can refine your search with the options on the left of the results page.
Searching for Members?
You entered an email address. Would you like to search for members? Click Yes to continue. If no, materials will be displayed first. You can refine your search with the options on the left of the results page.
