Data science is a field that extracts insights and knowledge from data. It’s like being a detective who uses clues (data) to solve mysteries (business problems or questions).
""", unsafe_allow_html=True) st.markdown("A farmer wanted to grow the best crops but didn’t know which seeds to plant. A scientist helped by collecting data on soil, temperature, and rainfall, and used that data to give the farmer advice on when to plant and water the crops.
Just like the scientist analyzed data to guide the farmer, data science uses data to find patterns and make decisions, helping solve problems and predict outcomes.
""", unsafe_allow_html=True) st.markdown("There was a mother and her young daughter who didn’t know how to draw. Wanting to help, the mother enrolled her daughter in a drawing class. At the class, the teacher showed her step-by-step how to draw simple shapes and pictures. The girl practiced every day, observing and mimicking what her teacher showed. Over time, she improved and could create beautiful drawings on her own. This was possible because of the natural intelligence given by God—her ability to learn, practice, and create. ✍️✨
Similarly, in Artificial Intelligence (AI), machines do not have natural intelligence to learn or create on their own. Just as the mother guided her daughter by enrolling her in classes and the teacher helped her practice, we guide machines by feeding them data and teaching them patterns. Over time, the machine learns from this data and mimics natural intelligence to perform tasks intelligently.
""", unsafe_allow_html=True) st.image("https://huggingface.co/spaces/hari3485/DiveIntoML/resolve/main/image.png") # Key Points st.markdown("""ML acts as a guide for machines, helping them learn from data using algorithms. It uses step-by-step instructions provided by the guide (algorithm). ML identifies relationships mathematically, considered as a function.
Key Requirements:
When both conditions are met, ML finds the relationship between inputs (features) and outputs (class labels). Inputs are called features, and outputs are called class labels. ML learns a function to understand how inputs and outputs are related.
""", unsafe_allow_html=True) st.markdown("Machine Learning (ML) is like a teacher who uses past exam results to find patterns and help students improve. By analyzing how study habits affect grades, the teacher creates a system that suggests personalized study tips. Similarly, ML uses past data to identify patterns and make predictions, like Netflix recommending movies based on your viewing history.
""", unsafe_allow_html=True) # DL Section st.markdown("DL extends ML by adding a logical structure called neurons. These neurons process inputs, compute relationships, and produce outputs. It is a subfield of both AI and ML.
""", unsafe_allow_html=True) st.markdown("Deep Learning (DL) is like learning from experience instead of just following rules, unlike Machine Learning (ML), which follows fixed instructions. DL uses systems that improve over time by processing data and recognizing patterns. A real-life example is self-driving cars, which learn to navigate and make decisions by processing data and getting better with experience.
""", unsafe_allow_html=True) # App Title st.markdown("Generative AI is a transformative technology designed to mimic human-like learning and creativity by leveraging Machine Learning (ML) and Deep Learning (DL) techniques. It focuses on generating new content such as:
Tools like ChatGPT, Gemini, and Meta AI exemplify its capabilities in natural language processing and content generation.
""", unsafe_allow_html=True) # Key Feature with examples st.markdown("""Generative AI represents the next step in technological evolution. By mastering its concepts, individuals can create systems that mimic human creativity, enhance decision-making, and solve real-world problems in innovative ways.
""", unsafe_allow_html=True)