Queensland University of Technology
Asked 6th Mar, 2016
What is the pros and cons of Convolutional neural networks?
Hi researchers! I am a learner of statistics learing and machine learning. After applying the Convolutional neural networks into image recognition and text mining, I think this method is powerful in classification. So I want to apply them into statistics field and want to know the advantages and disadvantages of CNNs. Can I view it as a specia kind of "regression", which is blessed with flexible model form and interaction form？ What is the disadvantage of it? Thank you very much!
Most recent answer
Popular answers (1)
Top contributors to discussions in this field
All Answers (10)
Conference Paper Twitter Sentiment Analysis with Deep Convolutional Neural Networks
One of the weaknesses was pointed out by Severyn et al. (link above).
It was the dependence of CNNs on the initial parameter tuning (for a good point) to avoid local optima. Thus, a weakness of CNNs is the considerable amount of work they require to initialize according to the problem at hand. This would require some expert knowledge in the domain.
Similar questions and discussions
What are Convolutional Neural Networks (CNN) weakness?
- Giorgio Roffo
Convolutional neural networks like any neural network model are computationally expensive. But, that is more of a drawback than a weakness. This can be overcome with better computing hardware such as GPUs and Neuromorphic chips.
So, what are Convolutional Neural Networks weakness?
Missing theory, Reasoning, Memory, Unsupervised learning, ...
A theory to explain why and how these deep architecture work is actually missing? For instance, this theory can be relevant in understanding how much data or how many layers are needed to achieve a certain performance.
Grid for the evaluation of literature reviews
- Sandrine Roussel
Could some of you recommend a grid (or several) for the "evaluation" of literature reviews?
Thank you very much.
How to add PLA, ABS and other thermoplastic in Ansys Workbench?
- Nekin Joshua
I cannot find the PLA material in ansys. I tried to add PLA in library. After that also it shows error in PLA properties.
Please tell the way to add the PLA, ABS in Ansys workbench.
Could please direct me to several articles that cover the impact of particle size on magnetite oxidation?
- Abdellatif Laarich
the effect of particle size on magnetite oxidation.
Pesticide resistance among pests and natural enemies
- Syed Rizvi
Why do natural enemies are generally more adversely affected by chemical insecticides than the target pest?
I understand there could be several factors involved but can someone discuss a few of them and refer some good papers on it.
What are the statistical models that can be used to analyze the relationship between few time series variables?
- Randimal Herath
In my time series dataset, I have 1 dependent variable and 5 independent variables and I need to find the independent variable that affects the dependent variable the most (the independent variable that explains most variations in the dependent variable). Consider all 5 variables are economic factors.
Any advice - the solver engine was unable to converge on a solution for the nonlinear problem as constrained. please see the troubleshooting section?
- Abhilashsharan Tambak
I am a beginner ANSYS user.. I want to simulate "Friction Stir Welding" in ANSYS. But I am getting error that "the solver engine was unable to converge on a solution for the nonlinear problem as constrained. Please see the Troubleshooting section of the Help System for more information."
I am doing something wrong.. but I have no idea what it is.. Do you have any suggestions for me?
Any suggestions will be highly appreciated.
Die Computergraphik beschäftigt sich neben der Herstellung 'echt' wirkender Bilder neuerdings auch mit sog. nichtrealistischen Darstellungen.
Die gesamte Diplomarbeit ist ein Demonstrationsmodell. Es gelang Algorithmen zu finden, mit denen man auf optischem Wege Unterschiede zwischen einer Werbesendung und dem normalen Fernsehprogramm erkennen konnte.