![]() Here it seems MATLAB has taken a lot of trust away from the user, handling a lot of tensor processing in a way which is hidden and without regard for the users application. Here you have it being a tool solely for vectorising sequence data, when in truth a Flatten layer can (and often should) be used with any data structure as a method of ensuring the correct tensor shape at the output layer. The "Flatten" layer is a good example of this. ![]() To further compound the previous issue, certain layer functionalities seem to have been misunderstood.(As I write this I am aware that any real-valued data can be given to an ImageInputLayer, but the point still stands: give the most functionality to the user and do not limit the applications of deep learning to image processing only) Have an input layer which handles data normalisation or standardisation is a great idea, but it should be generic and not constrain the user to any data type, or even any data format. The invention of the Deep Network Designer was inspired, however limiting functionality of such deep networks by using "ImageInputLayers" is both misleading and in poor judgement. While the use of deep network designs in image processing has been both widely accepted and largely successful, limiting the use of densely connected layers or convolutional layers to image processing only is equivalent to handing someone a phone and saying all it can do is take pictures. The limitation of layers or network topographies to only certain tasks is a very big mistake from a design point.The same is true of all data sets, yet no few examples in the MATLAB documentation have the Validation data set being a subset of the Training data set. No presentation or data-point in the Training set can be allowed to repeat in either the validation or testing sets. The most rudimentary of Deep-Learning guides will go to great lengths to make sure the reader knows that all datasets are to be completely exclusive of one another. The conflation of training and validation data.Key concepts of Deep-Learning and the functionality of various layers and network topographies are completely misrepresented in your documentation. To the best of my understanding, it seems as though the developers haven't taken inspiration or followed the lead of those already in this field. However the Deep-Learning tools developed in Python do surpass those developed in MATLAB. Of the languages I've worked in MATLAB provides some of the best tools for most any industrial setting, keeping code clean, legible and easily read with an efficacy not matched by Python. so all being equal, the argument of free vs. You've already "paid" for MATLAB, whether it's through work, school, or another program.As a student or researcher, this is generally more acceptable Paying for MathWorks technical support gives you easier and more consistent access to the same, especially if you're not capable/have no time to jump into a code base and debug/fix issues on your own. In open-source software, you can seek assistance from the online community and report issues on e.g.working with software that has a release cycle for all toolboxes at once, and a dedicated quality engineering team Think about the risks of cobbling together constantly evolving experimental software vs. You are working in an industry/on a product where open-source software may not meet certain certification/quality criteria, but perhaps working with commercial software is preferred.You are using other MathWorks tools that are more unique/established (such as Simulink, Stateflow, controls, signal processing, etc.) and want easy integration.You are already comfortable with MATLAB and the functionality in Deep Learning Toolbox can solve your problem (this could often mean you're not necessarily pushing the boundaries of deep learning, but rather solving a problem with commonly available techniques that are already in these tools).when should you use MathWorks' deep learning solution?
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |