What are possible deep learning methods for classification?
I have solved the problem using convolutional LSTM, and compared the accuracy with three baseline deepnet methods (MLP, CNN, LSTM). Now my paper cameback after the review, and reviewer asked to make comparison with more deepnet methods. What are other methods from which I can make comparison?
Asif Nawaz ,
You could try a deep RBM or other variations of LSTM. Though I find it curious that you basically have several baseline methods and they asked for more.
if you are talking about image classification for example, there are many powerful models such as AlexNet and ResNet for example, that achieve state of art results in this field.
Dear Asif Nawaz ,
Here are classification algorithms in Machine Learning
- Linear Classifiers: Logistic Regression, Naive Bayes Classifier.
- Nearest Neighbor.
- Support Vector Machines.
- Decision Trees.
- Boosted Trees.
- Random Forest.
- Neural Networks.
Use end to end encryption advanced architecture such as AlexNet, VGG16, GoogleNet, etc., which gives highest accuracy especially for classification problem.
We have also faced the same problem (when we have applied for reasonably good journal) where we have used old machine learning algorithms.
The newly developed deep learning architectures automatically learns features and yields sound accuracy with less confusion. Hope this clarifies your query.
- Xception
- VGG16
- VGG19
- ResNet, ResNetV2
- InceptionV3
- InceptionResNetV2
- MobileNet
- MobileNetV2
- DenseNet
- NASNet
And the list goes on.
You can use one of this model MobileNet, WRN and Shuffle-exchange network (SEN)
- Badges
- Science topic
- Similar topics
- Data Mining
- Classification