Spaces:
Sleeping
Sleeping
Update pages/1_Introduction.py
Browse files- pages/1_Introduction.py +8 -7
pages/1_Introduction.py
CHANGED
|
@@ -6,19 +6,19 @@ uploaded_image = st.file_uploader("Upload an image", type=["png", "jpg", "jpeg"]
|
|
| 6 |
|
| 7 |
if uploaded_image is not None:
|
| 8 |
image = Image.open(uploaded_image)
|
| 9 |
-
|
| 10 |
# Title and introduction
|
| 11 |
st.title('Understanding Machine Learning: Teaching Machines Like Children')
|
| 12 |
-
|
| 13 |
st.write("""
|
| 14 |
Machine Learning (ML) is like teaching a child to recognize things by showing examples. Imagine a father showing pictures of dogs and cats to his child, saying 'This is a dog' or 'This is a cat'. The child learns by associating the image with the label. Similarly, machines learn from data through two main types of learning: **Supervised** and **Unsupervised Learning**.
|
| 15 |
|
| 16 |
In this app, we'll use the analogy of a father teaching his child to explain these key ML concepts.
|
| 17 |
""")
|
| 18 |
-
|
| 19 |
# Display the image
|
| 20 |
st.image(image, caption='A father teaching his child by showing dog and cat pictures', use_column_width=True)
|
| 21 |
-
|
| 22 |
# Supervised Learning Explanation
|
| 23 |
st.header('Supervised Learning')
|
| 24 |
st.write("""
|
|
@@ -30,7 +30,7 @@ if uploaded_image is not None:
|
|
| 30 |
|
| 31 |
Over time, the child (or machine) becomes better at recognizing dogs, even if shown new pictures. The machine adjusts its internal model to predict the correct label for unseen data.
|
| 32 |
""")
|
| 33 |
-
|
| 34 |
# Unsupervised Learning Explanation
|
| 35 |
st.header('Unsupervised Learning')
|
| 36 |
st.write("""
|
|
@@ -42,7 +42,8 @@ if uploaded_image is not None:
|
|
| 42 |
|
| 43 |
Unsupervised learning helps the machine find structure in data without needing labeled examples.
|
| 44 |
""")
|
| 45 |
-
|
| 46 |
# Conclusion
|
| 47 |
st.write("""
|
| 48 |
-
Machine Learning mirrors how humans, especially children, learn by observing and being guided. This analogy helps simplify the complex concepts behind
|
|
|
|
|
|
| 6 |
|
| 7 |
if uploaded_image is not None:
|
| 8 |
image = Image.open(uploaded_image)
|
| 9 |
+
|
| 10 |
# Title and introduction
|
| 11 |
st.title('Understanding Machine Learning: Teaching Machines Like Children')
|
| 12 |
+
|
| 13 |
st.write("""
|
| 14 |
Machine Learning (ML) is like teaching a child to recognize things by showing examples. Imagine a father showing pictures of dogs and cats to his child, saying 'This is a dog' or 'This is a cat'. The child learns by associating the image with the label. Similarly, machines learn from data through two main types of learning: **Supervised** and **Unsupervised Learning**.
|
| 15 |
|
| 16 |
In this app, we'll use the analogy of a father teaching his child to explain these key ML concepts.
|
| 17 |
""")
|
| 18 |
+
|
| 19 |
# Display the image
|
| 20 |
st.image(image, caption='A father teaching his child by showing dog and cat pictures', use_column_width=True)
|
| 21 |
+
|
| 22 |
# Supervised Learning Explanation
|
| 23 |
st.header('Supervised Learning')
|
| 24 |
st.write("""
|
|
|
|
| 30 |
|
| 31 |
Over time, the child (or machine) becomes better at recognizing dogs, even if shown new pictures. The machine adjusts its internal model to predict the correct label for unseen data.
|
| 32 |
""")
|
| 33 |
+
|
| 34 |
# Unsupervised Learning Explanation
|
| 35 |
st.header('Unsupervised Learning')
|
| 36 |
st.write("""
|
|
|
|
| 42 |
|
| 43 |
Unsupervised learning helps the machine find structure in data without needing labeled examples.
|
| 44 |
""")
|
| 45 |
+
|
| 46 |
# Conclusion
|
| 47 |
st.write("""
|
| 48 |
+
Machine Learning mirrors how humans, especially children, learn by observing and being guided. This analogy helps simplify the complex concepts behind teaching machines to recognize patterns and make decisions. Just like the child learns over time, machines improve as they are exposed to more data.
|
| 49 |
+
""")
|