Scribd
Upload
3 views2 pages

Deep Vs Shallow Learning

The document contrasts shallow learning and deep learning in machine learning. Shallow learning involves simpler models with manual feature extraction, suitable for small, structured datasets, while deep learning utilizes complex neural networks to automatically learn from large, unstructured data. Examples of shallow learning include Logistic Regression and SVM, whereas deep learning examples include CNN and LSTM.

Uploaded by

yashbansal0859
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views2 pages

Deep Vs Shallow Learning

The document contrasts shallow learning and deep learning in machine learning. Shallow learning involves simpler models with manual feature extraction, suitable for small, structured datasets, while deep learning utilizes complex neural networks to automatically learn from large, unstructured data. Examples of shallow learning include Logistic Regression and SVM, whereas deep learning examples include CNN and LSTM.

Uploaded by

yashbansal0859
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Deep vs Shallow Learning

Shallow Learning: Shallow learning uses models with one or two layers (excluding input and output
layers). It relies heavily on manual feature extraction.

Example of Shallow Learning, If we use Logistic Regression or SVM with manually selected features like
BMI, glucose, insulin.

Shallow Learning can be used when:

• Dataset is small
• Problem is structured/tabular
• Interpretability is important (e.g., medical decision support)

Examples of shallow learning algorithms:

• Support Vector Machine


• Logistic Regression
• Decision Tree
• k-Nearest Neighbors

Deep learning: is a subset of machine learning that uses artificial neural networks with multiple hidden
layers (deep neural networks). It can automatically learn features from raw data.

If we use a Deep Neural Network that automatically learns feature interactions from raw clinical data
then it Deep Learning approach.

Medical images such as retinal scans using CNN.

Time-series glucose monitoring data using LSTM

Deep learning can be used when:

• Dataset is large
• Data is unstructured (images, audio, text)
• High accuracy is required
• Computational resources are available

Examples of deep learning models:

• Convolutional Neural Network (CNN)


• Recurrent Neural Network (RNN)
• Long Short-Term Memory (LSTM)
• Deep Neural Network (DNN)

You might also like