Spaces:
Sleeping
Sleeping
Update pages/Machine Learning vs Deep Learning.py
Browse files
pages/Machine Learning vs Deep Learning.py
CHANGED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
import pandas as pd
|
| 3 |
+
|
| 4 |
+
# Define the table data
|
| 5 |
+
data = {
|
| 6 |
+
"Aspect": [
|
| 7 |
+
"Learning Approach", "Data Requirement", "Complexity of Tasks",
|
| 8 |
+
"Computation Power", "Algorithms Used", "Training Time", "Data Types Processed"
|
| 9 |
+
],
|
| 10 |
+
"Machine Learning (ML)": [
|
| 11 |
+
"Uses a statistical approach to analyze data and make predictions.",
|
| 12 |
+
"Works well with smaller datasets.",
|
| 13 |
+
"Handles simpler relationships (e.g., predicting house prices).",
|
| 14 |
+
"Can run on CPUs (low computational power).",
|
| 15 |
+
"Uses models like KNN, Decision Trees, Linear Regression.",
|
| 16 |
+
"Faster training due to simpler computations.",
|
| 17 |
+
"Works with structured/tabular data."
|
| 18 |
+
],
|
| 19 |
+
"Deep Learning (DL)": [
|
| 20 |
+
"Uses neural networks to automatically learn patterns.",
|
| 21 |
+
"Requires large amounts of data to perform well.",
|
| 22 |
+
"Handles complex relationships (e.g., object recognition in images).",
|
| 23 |
+
"Requires GPUs/TPUs (high computational power).",
|
| 24 |
+
"Uses ANN, CNN, RNN for feature extraction and learning.",
|
| 25 |
+
"Longer training time due to deep layers and complex processing.",
|
| 26 |
+
"Works with images, videos, text, and audio."
|
| 27 |
+
]
|
| 28 |
+
}
|
| 29 |
+
|
| 30 |
+
# Create DataFrame
|
| 31 |
+
df = pd.DataFrame(data)
|
| 32 |
+
|
| 33 |
+
# Display the table in Streamlit
|
| 34 |
+
st.title("Machine Learning vs. Deep Learning")
|
| 35 |
+
st.write("### Comparison Table")
|
| 36 |
+
st.table(df)
|
| 37 |
+
|
| 38 |
+
# Convert DataFrame to HTML
|
| 39 |
+
html_table = df.to_html(index=False, escape=False)
|
| 40 |
+
|
| 41 |
+
# Display HTML table
|
| 42 |
+
st.write("### HTML Representation")
|
| 43 |
+
st.code(html_table, language="html")
|