Update pages/Difference_between_ML&DL.py

pages/Difference_between_ML&DL.py

@@ -1,15 +1,17 @@
 import streamlit as st
 st.markdown("<h1 style='text-align: center; color: Balck;'>Difference between ML & DL</h1>", unsafe_allow_html=True)
 table = """
-| **Aspect**               | **Machine Learning**                              | **Deep Learning**                              |
+| **Contents**               | **Machine Learning**                              | **Deep Learning**                              |
 |---------------------------|--------------------------------------------------|-----------------------------------------------|
-| **Definition**            | Subset of AI focused on learning patterns in data. | Subset of ML using neural networks with multiple layers. |
-| **Data Dependency**       | Works well with smaller datasets.                 | Requires large datasets to perform well.      |
-| **Feature Engineering**   | Manual feature engineering is often required.     | Automatically extracts features from raw data. |
-| **Model Interpretability**| Models are more interpretable and easier to debug.| Models are often considered "black boxes."    |
-| **Hardware**              | Runs efficiently on CPUs.                         | Requires GPUs or TPUs for faster computation. |
-| **Complexity**            | Suitable for simpler tasks like linear predictions. | Suitable for complex tasks like image or speech recognition. |
-| **Training Time**         | Training time is generally shorter.               | Training time can be very long.               |
-| **Examples**              | Spam detection, fraud detection, basic predictions.| Image recognition, autonomous vehicles, NLP.  |
+| **Concept**               | ML use statistical concepts to copy learning ability.|DL uses logical structure called as Neuron to copy learning
+| **Algorithm**             | It requires ML Algorithm and data to create mode .| It requires DL Algorithm and data to create mode|
+| **Data sets**             |It work on small data sets.                        | It work on large data sets.                   |
+| **performance**           | ML have a limit in giving performance.            | ML have a limit in giving performance   |
+| **Data**                  | The Data should be in Tabular format that is structured data.| Directly deals with unstructured data |
+| **Memory**                | Less memory is used.                              | More memory is used . |
+| **Training Time**         | ML has less training time.                        | DL has more training time.               |
+| **Hardware**              |ML can run CPU.                                    | DL can run on GPU.  |
+| **Interpretability**      |Models are more interpretable and easier to debug. | Models are often considered "black boxes.|
+| **Examples**              |Spam detection, fraud detection, basic predictions.|Image recognition, autonomous vehicles, NLP.
 """
 st.markdown(table)