Once a clear understanding of the problem is established, design the architecture based on the theory youve learnt.
I would highly recommend Andrew Ngs Machine Learning, Deep Learning specialization on Coursera to get a good head-start on theory as well as its implementation.
Once the model is trained, check the results on validation dataset in order to estimate the performance.
Determine if the model is suffering from any of the under-fitting or over-fitting issues.
Brief description of over-fit and under-fit is provided below.
Fine-tune the parameters/layers accordingly.
Also, check if there is any pattern on cases where the algorithm fails.
You could modify your algorithm accordingly.
For instance, if your face detection algorithm doesnt work for faces captured in the slightly darker region of an image, you could apply image pre-processing (color based) algorithms that would help the model to overcome the issue.
Your model/architecture is suffering from under-fitting issue if both your training and validation accuracy is relatively low.
For instance, if the training and validation accuracy is about 75% for distinguishing cats and dogs in a particular database where the benchmark is about 99%, your algorithm is considered to be suffering from under-fitting issue.
Some of the remedies to overcome this are as follows: (i) get more training data (could be augmented), (ii) calculate more features, (iii) calculate polynomial based features, (iv) reduce the value of the regularization parameter, (v) add more layers (in case youre developing a deep learning based architecture) after observing the results provided at each layer, (vi) Add pre-processing methods that could be useful to distinguish the classes Your model/architecture is suffering from over-fitting issue if training accuracy is high and validation accuracy is considerably lower.
For instance, if the training accuracy is about 99% and validation accuracy is about 80%, your algorithm is considered to be suffering from over-fitting issue.
Some of the remedies to overcome this are as follows: (i) get more labeled training data, (ii) remove certain features, (iii) apply feature selection approaches to select a subset of features for classification, (iv) apply regularization or increase its value, (v) remove certain layers (in case youre developing a deep learning based architecture) after observing the results provided at each layer, (vi) Apply dropout regularization Once youre done fine-tuning the parameters, hyperparameters according to the performance on validation dataset, test your algorithm on the data that it has never seen.
It will provide the true performance of your algorithm.
If the performance is good, you could deploy it for use in real-time or publish it in a conference/journal.
Test the algorithm under different conditions, databases and make it as robust as possible.
Also, get feedback from user/peer researchers for improvisation.
Bio: Barath Narayanan is an Associate Research Scientist at University of Dayton Research Institute and Adjunct Faculty at University of Dayton.
He has 6+ years of experience in applying effective machine learning and deep learning algorithms for various applications.
Original.
Reposted with permission.
Related: var disqus_shortname = kdnuggets; (function() { var dsq = document.
createElement(script); dsq.
type = text/javascript; dsq.
async = true; dsq.
src = https://kdnuggets.
disqus.
com/embed.
js; (document.
getElementsByTagName(head)[0] || document.
getElementsByTagName(body)[0]).
appendChild(dsq); })();.. More details