Update pages/2.Introduction to Data Science.py

pages/2.Introduction to Data Science.py

@@ -51,7 +51,7 @@ st.write("""
 st.subheader(":red[**Types of Machine Learning**]")
 st.write("Machine Learning can be divided into three main types based on how the model learns from data:")
 
-st.subheader("**1. Supervised Learning**")
+st.subheader(":blue[**1. Supervised Learning**]")
 st.write("In supervised learning, the machine is trained using labeled data, meaning the data comes with input-output pairs. The model learns to predict the output from the input by identifying patterns in the data.")
 st.write("""**Examples:** 
 - Predicting house prices based on size, location, and number of rooms.
@@ -62,7 +62,7 @@ st.subheader("**Types of Supervised Learning:**")
 st.write("**1.Regression:** Predicting continuous values.Example: Predicting a person’s salary based on their experience.")
 st.write("**2.Classification:** Predicting discrete categories.Example: Determining whether an email is spam or not.")
 
-st.subheader("**2. Unsupervised Learning**")
+st.subheader(":blue[**2. Unsupervised Learning**]")
 st.write("In unsupervised learning, the data has no labels. The model identifies hidden patterns or groups within the data without guidance.")
 st.write("""**Examples:**
 - Customer segmentation: Grouping customers based on their buying behavior.
@@ -73,11 +73,41 @@ st.subheader("**Types of Unsupervised Learning:**")
 st.write("**1.Clustering:** Grouping data points into similar clusters.Example: Grouping movies by genre based on viewers’ preferences.")
 st.write("**Dimensionality Reduction:** Reducing the number of features in the data.Example: Compressing image data for faster processing.")
 
-st.subheader("**3. Reinforcement Learning**")
+st.subheader(":blue[**3. Reinforcement Learning**]")
 st.write("Reinforcement learning is about learning by trial and error. The model learns to make a sequence of decisions to maximize a reward.")
 st.write("""**Examples:**
 - Learning to drive by interacting with the road environment.
 - Training a robot to walk by rewarding good steps.
 """)
-st.image("machine.jpg")
+
+
+st.subheader(":red[**What do you mean by Deep Learning**]")
+st.write("Deep Learning is a specialized field of Machine Learning where machines learn from data using structures called neural networks. These networks are designed to work like the human brain, with layers of "neurons" processing information step by step.It’s like teaching a machine to think by showing it lots of examples and letting it learn on its own.")
+st.write("""**Examples:** 1.Imagine you want a computer to recognize handwritten digits (like on checks):
+- Input Data: Provide many images of handwritten numbers with labels (e.g., “This is 5”).
+- Training: A neural network learns the patterns in these images, like the curves of "5."
+- Prediction: When you show it a new handwritten digit, it predicts what number it is.
+2.Understand and respond to your voice using deep learning.
+3.Unlocking your phone by recognizing your face.
+4.Identifying diseases from X-rays or MRI scans.
+5.Suggesting what to watch next based on your viewing history.
+""")
+
+st.subheader(":red[**Types of Neural Networks in Deep Learning**]")
+st.write(""":blue[**1.Convolutional Neural Networks (CNNs):**]
+- Used for image and video processing.
+- Detecting objects in photos, like identifying dogs in an image.
+""")
+st.write(""":blue[**2.Recurrent Neural Networks (RNNs):**]
+- Used for sequential data, like text or speech.
+- Predicting the next word in a sentence (e.g., in chat apps).
+""")
+st.write(""":blue[**3.Generative Adversarial Networks (GANs):**]
+- Used to create new data similar to what it has seen.
+- Generating realistic images of non-existent people.
+""")
+st.write(""":blue[**4.Transformers:**]
+- Used for language tasks, powering tools like ChatGPT.
+- Translating languages or summarizing text.
+""")