| import streamlit as st | |
| import numpy as np | |
| import pandas as pd | |
| st.header(":red[**Difference between Machine learning and deep learning**]") | |
| st.write("Here are the key differences between Machine Learning (ML) and Deep Learning (DL)") | |
| st.write(""" | |
| 1. Definition: ML is a subset of AI that focuses on learning patterns from data, while DL is a subset of ML that uses neural networks to mimic the human brain. | |
| 2. Data Requirement: ML performs well with small to medium datasets, whereas DL requires large datasets for accurate results. | |
| 3. Feature Engineering: In ML, feature selection is done manually, while DL automatically extracts features from raw data. | |
| 4. Model Complexity: ML uses simpler algorithms like regression or decision trees, whereas DL uses complex models with multiple layers (neural networks). | |
| 5. Hardware: ML works on regular computers, but DL requires specialized hardware like GPUs or TPUs for faster processing. | |
| 6. Performance: ML struggles with unstructured data, while DL excels in handling unstructured data like images, videos, and text. | |
| 7. Training Time: ML models train faster, while DL models often require significantly more time to train. | |
| 8. Applications: ML is used for tasks like fraud detection, price predictions, and recommendations. DL is used for advanced tasks like face recognition, self-driving cars, and language translation. | |
| """) | |