CHATGPT/GENERATIVE AI

Name : U. Sandhya Rani(21F01A4661)

Company Name : IIDT-Blackbucks
Date:18-11-2024
 CHATGPT TASKS
Task 1:Introduction To AI&ML

Description: Artificial Intelligence (AI) and Machine Learning (ML) are rapidly evolving
fields that enable machines to mimic human intelligence and learn from data. AI
focuses on creating systems that can perform tasks requiring human-like intelligence,
while ML is a subset of AI that uses algorithms to analyze data, identify patterns, and
make predictions or decisions with minimal human intervention.
Outcomes:
Understanding Core Concepts: Gain foundational knowledge of AI and ML, their
differences, and real-world applications.
Problem-Solving Skills: Learn how to approach problems using AI and ML methods.
Hands-on Experience: Get practical exposure to implementing basic machine
learning models.
Future Trends: Be aware of emerging trends and advancements in AI & ML.
 Task 2: ML Classification Models & Clustering

Description:: Machine Learning (ML) Classification and Clustering are two key techniques used for data analysis and
prediction.
Classification involves training models to categorize data into predefined labels or classes. Algorithms like Decision
Trees, Support Vector Machines, and Neural Networks are commonly used.
Clustering is an unsupervised learning approach where data points are grouped based on similarity without prior
labels. Popular clustering algorithms include K-Means, Hierarchical Clustering, and DBSCAN.

Outcomes:
Model Selection Skills: Learn when to apply classification algorithms vs. clustering for solving various data problems.
Practical Knowledge: Gain hands-on experience with building and evaluating models for classification and clustering .
.
 Task3:Introduction to Data Analysis Techniques

Description: Data analysis involves examining, organizing, and interpreting data to uncover valuable
insights, identify trends, and make informed decisions. This introduction provides a foundation for
understanding common techniques used in data analysis, emphasizing their applications in real-world
problem-solving.
Key Topics:
Data cleaning and preprocessing
Descriptive statistics and visualization
Exploratory data analysis (EDA)
Outcomes:
Enhanced Understanding: Gain clarity on core data analysis concepts and methods.
Skill Development: Learn basic techniques like data summarization, pattern identification, and
visualization.
Practical Applications: Apply these techniques to interpret data and derive actionable insights.
 Task4:Introduction to Data Visualization

Description: It is the graphical representation of information and data, using visual elements such as
charts, graphs, and maps. It enables better understanding, communication, and interpretation of
complex data by revealing patterns, trends, and outliers in a clear and intuitive manner.
Key Topics:
Importance of data visualization in decision-making
Common visualization tools and techniques (e.g., bar charts, line graphs, scatter plots)
Principles of effective visual design (clarity, simplicity, accuracy)
Interactive and dynamic visualizations
Outcomes:
Enhanced Data Interpretation: Understand data better through visual representation.
Improved Communication: Learn how to convey insights effectively to diverse audiences.
Skill Development: Get acquainted with tools like Tableau, Power BI, or Python libraries (e.g.,
Matplotlib, Seaborn).
Foundation for Storytelling: Use visuals to create compelling data-driven narratives.
 Task5: Neural Networks

Description : Neural networks are computational models inspired by the human brain, designed to
recognize patterns and solve complex problems.
They consist of layers of nodes (neurons) that process input data, learn through training, and make
predictions or decisions.
Commonly used in applications such as image recognition, natural language processing, and
autonomous systems.
Outcomes:
Improved Efficiency: Automates tasks like data classification, prediction, and pattern detection
with high accuracy.
Adaptability: Learns from data to improve performance over time.
Broad Applications: Powers advancements in AI, enabling breakthroughs in medicine, finance, and
more.
 Task6:Deep Learning

Description : Deep learning is a subset of machine learning that uses artificial neural networks with
multiple layers to model complex patterns in data.
It excels in tasks involving large datasets and unstructured data like images, text, and audio.
Common architectures include Convolutional Neural Networks (CNNs) for image processing and
Recurrent Neural Networks (RNNs) for sequence data.
Outcomes:
Enhanced Accuracy: Achieves superior performance in tasks like image recognition, speech
processing, and language translation.
Automated Feature Extraction: Eliminates the need for manual feature engineering by learning
directly from raw data.
Real-World Impact: Enables breakthroughs in areas like self-driving cars, medical diagnostics, and
personalized recommendations.Add supporting visuals like a layered neural network structure or
examples of applications for a visually appealing slide.
 Task7:Mad Lib Generator

Description:A Mad Lib generator is a fun, interactive application that creates customizable
stories by prompting users to input words like nouns, verbs, and adjectives.
 It uses placeholders in a predefined story template, which are dynamically replaced with
user-provided words to generate humorous or unique narratives.
 Often developed as a beginner programming project to learn concepts like string
manipulation, input handling, and data structures.
Outcomes:
 Enhanced Creativity: Encourages playful and creative storytelling by allowing users to craft
unique narratives.
 Programming Skills Development: Teaches foundational concepts in coding, including
input/output handling and logic building.
 Engagement and Fun: Provides an entertaining way to combine language and technology,
suitable for all age groups.
Include an example of a short Mad Lib story on the slide for engagement.
 Task8: Mad Lib Generator : Algorithm and Dataset

Algorithm:
1.Import Libraries
•Use randint (random word selection) and deepcopy (preserve dictionary).
2.Define Story Template
•Create a story with placeholders (e.g., {adjective}, {noun}).
3.Create Word Dictionary
•Predefine word lists categorized by parts of speech.
4.Select Words
•get_word(type, local_dict): Randomly selects and removes words to avoid repetition.
5.Create Story
•create_story():
•Copies the dictionary, selects words, and fills the template.
6.Generate and Print
•Print the final Mad Libs story.
 Task9:Data set with code and output

Dataset : Predefined word dictionary (no external dataset).

Output:
Code:
 Conclusion

Summary:
Summarize key takeaways from your internship experience:
Core projects worked on
Skills developed
Personal growth and insights into generative AI.
Future Work:
Mention how you plan to continue learning or developing in the field of AI.
Recommendations:
Provide any recommendations based on your experience (e.g., improvements to
current processes, further research, or investment in AI tools).
 References

Site Resources:
List all references used during your internship for research, tools, or concepts
(e.g., books, research papers, online tutorials).
Example:
"Generative Pretrained Transformers," OpenAI Documentation.
"Deep Learning with Python," François Chollet.