Feature engineering vs Feature Learning (tips tricks 46 )
Ғылым және технология
Code generated in the video can be downloaded from here:
github.com/bnsreenu/python_fo...
All other code:
github.com/bnsreenu/python_fo...
Feature engineering refers to the process of selecting and designing relevant features from raw data to improve the performance of machine learning algorithms. It involves domain expertise and creativity to identify informative features that capture the underlying patterns in the data.
On the other hand, feature learning, also known as representation learning, is a technique that enables a machine learning model to automatically learn relevant features from raw data. It involves using neural networks to discover useful features that can be used for downstream tasks.
This video tutorial demonstrates that with enough knowledge, features can be engineered from images using handcrafted algorithms. However, the tutorial also shows that pre-trained networks such as VGG16, which were trained on large datasets, can automatically learn rich features from images with no prior knowledge. This illustrates the power of feature learning, where pre-trained models can be leveraged to extract informative features, making it a more efficient and effective method than feature engineering.
Related tutorials:
• 158 - Convolutional fi...
• 158b - Transfer learni...
• 159 - Convolutional fi...
• 159b - Pretrained CNN ...
Пікірлер: 29
Good to see u after long time sir
I appreciate you very much for your tutorials!
This is the kind of topic I take for granted. Thank You sir
Thanks for the effort you put in i really like your content 🤗
Very useful for my application in OCT images. Thanks a lot
This is so cool and useful it will help mi a lot understanding my models
Thanks for making this video
you sir genius! hats off
Dziękujemy.
@DigitalSreeni
Жыл бұрын
Thank you
Great video!
@DigitalSreeni
Жыл бұрын
Glad you enjoyed it
Thank you sir🤝🤝🤝
big fan sir
Thanks
Teşekkürler.
@DigitalSreeni
Жыл бұрын
Thank you
How do you segment an Invasive Ductal Carcinoma (IDC) Breast cancer whole slide image for the purpose of grading. And how do you extract features using VGG16
great view
@DigitalSreeni
Жыл бұрын
Thank you.
Please start NLP series
Hi Sir, Always you give very informative video with explanation and code. It's Good. Can you please make a video on custom dataset with say 1000 images to generate filtered responses using VGG16 ? Thank You.
Sreeni, would it be more "feature rich" to train a model to reconstruct only this image. OR is it richer to use a model trained with imagenet
@DigitalSreeni
Жыл бұрын
If you train on only one image or one type of image, it will be feature rich at that specific image.
Hi sir, if possible plz start course on NLP..from beginner to advanced..
Hi, Do you have any codes /videos on NLP or suggestions
@DigitalSreeni
Жыл бұрын
English text prediction: kzread.info/dash/bejne/rK130tCtk7mxg9I.html Hindi (and Telugu) text: kzread.info/dash/bejne/hWl4yMSeYK-9aJM.html
@chitrranshia7765
Жыл бұрын
@@DigitalSreeni looking for toxic comment classification
Hey sir, i am using your ensemble learning code for Binary classification. I am having problem in getting ensemble accuracy. The three models gives me 0.94, 0.91, 0.88 but the average ensemble = 0.46. I don't know the problem could you please help me point it out. model1 = load_model('saved_models/model1.hdf5') model2 = load_model('saved_models/model2.hdf5') model3 = load_model('saved_models/model3.hdf5') models = [model1, model2, model3] preds = [model.predict(X_test) for model in models] preds=np.array(preds) summed = np.average(preds, axis=0) # argmax across classes ensemble_prediction = np.argmax(summed, axis=1) prediction1 = model1.predict_classes(X_test) prediction2 = model2.predict_classes(X_test) prediction3 = model3.predict_classes(X_test) accuracy1 = accuracy_score(y_test, prediction1) accuracy2 = accuracy_score(y_test, prediction2) accuracy3 = accuracy_score(y_test, prediction3) ensemble_accuracy = accuracy_score(y_test, ensemble_prediction) print('Accuracy Score for model1 = ', accuracy1) print('Accuracy Score for model2 = ', accuracy2) print('Accuracy Score for model3 = ', accuracy3) print('Accuracy Score for average ensemble = ', ensemble_accuracy)