Scribd Logo
Upload

Welcome to Scribd!

  • 22 views

    Cap450:Artificial Intelligence and Intelligent Systems: Session 2023-24 Page:1/2

    Uploaded by

    roshankr9525940788
    ai project based on cnn rnn

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Cap450:Artificial Intelligence and Intelligent Systems: Session 2023-24 Page:1/2

    Uploaded by

    roshankr9525940788
    22 views2 pages
    ai project based on cnn rnn

    Original Title

    ai

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    ai project based on cnn rnn

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    22 views2 pages

    Cap450:Artificial Intelligence and Intelligent Systems: Session 2023-24 Page:1/2

    Uploaded by

    roshankr9525940788
    ai project based on cnn rnn

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 2

    CAP450:ARTIFICIAL INTELLIGENCE AND INTELLIGENT SYSTEMS

    L:2 T:0 P:2 Credits:3

    Course Outcomes: Through this course students should be able to

    CO1 :: recall key principles of AI, ML, and Python programming, and identify their roles in real-
    world scenarios through use cases.

    CO2 :: understand the techniques involved in data pre-processing, natural language processing,
    and neural networks, along with the challenges and opportunities they present.

    CO3 :: apply the learned techniques to build, optimize, and deploy neural networks, convolutional
    neural networks, and recommendation systems for practical AI applications.
    CO4 :: analyze the effectiveness of AI models through case studies, and design and implement
    AI solutions for chosen use cases, critically evaluating their impact and results.

    Unit I
    Introduction to Artificial Intelligence : Introduction to Al and Intelligent Agents, Search Methods
    and Knowledge Representation, Use Cases of Artificial Intelligence, Role of Machine Learning
    Engineer, Machine Learning Tools & Packages
    Python for Data Analysis : Python Data Structures, Python Programming Fundamentals, Python
    Packages, Working with NUMPY, Pandas, Data Visualization, Matplotlib and Seaborn
    Unit II
    Data Wrangling Techniques : Introduction to Data pre-processing, Importing the Dataset, Handling
    Missing data, Splitting the data into Train and Test set, Feature Scaling
    Natural Language Processing : Introduction to Natural Language Processing and NTLK, Bag of
    Words model, Natural Language Processing in Python, Sentiment analysis using Natural Language
    Processing
    Unit III
    Introduction to Neural Networks : Neuron and Activation Function, Neural Networks working and
    learning, Gradient Descent, Stochastic Gradient Descent and Backpropagation
    Recurrent Neural Networks : Introduction to Recurrent Neural Networks, The idea behind
    Recurrent Neural Networks, The Vanishing Gradient Problem, STMs and LSTM Variations Predicting
    Google stock prices using RNN, Evaluating, Improving, and Tuning the RNN
    Unit IV
    Convolutional Neural Networks : Introduction to Convolutional Neural Networks, Convolution
    Operation, ReLU Layer, Pooling, Flattening and Full Connection Classification of images using CNN,
    Evaluating, Improving, and Tuning the CNN
    Unit V
    Build & Deploy an Al Application : Introduction to different modes of Deployments, Working with
    Flask framework, Building an application with Flask Framework, Integrating Deep learning model with
    Web Application
    Unit VI
    Recommendation Systems : Collaborative Recommender System, Content-Based Recommender
    System, Designing of Recommender System
    Case Studies : Improving customer experience, Attrition Analysis for IBM, Movie Lens Dataset
    Analysis, Stock Market Data Analysis, Usecase1: Facebook Auto-Tagging/Face Recognition in Mobiles,
    Usecase2: Google Assistant, Usecase3: Youtube/Netflix/Amazon Recommendation Systems,
    Usecase4: Google Translate

    List of Practicals / Experiments:

    List of Practical
    • Install Python and required libraries (NumPy, Pandas, Matplotlib, Seaborn). Create a simple Python
    script for basic data manipulation. Explore Jupyter Notebooks for interactive coding and visualization.
    • Import a dataset using Pandas. Handle missing data and outliers. Split the dataset into training and
    testing sets. Perform feature scaling on numerical features.
    • Use NLTK for text processing in Python. Implement a Bag of Words model for text representation.
    Perform sentiment analysis on a sample dataset using NLP techniques.

    Session 2023-24 Page:1/2


    • Implement a simple neural network using TensorFlow or PyTorch. Understand the concept of
    neurons, activation functions, and backpropagation. Train the model on a small dataset and evaluate
    its performance.
    • Build an RNN model for time series prediction. Address the vanishing gradient problem using LSTM.
    Evaluate, improve, and tune the RNN for better predictions.
    • Implement a CNN for image classification. Understand convolutional operations, pooling, and
    flattening. Evaluate, improve, and tune the CNN for better accuracy.
    • Set up a Flask project for AI application deployment. Create a simple web interface for user
    interaction. Integrate a pre-trained deep learning model with the Flask application
    • Implement a collaborative recommender system using user-item interactions. Evaluate the
    recommendation system performance. Fine-tune parameters for better recommendations
    • Design and implement a content-based recommendation algorithm. Use user preferences and content
    features for personalized recommendations. Evaluate the system's effectiveness
    • Choose a use case (e.g., Facebook Auto-Tagging) from the syllabus. Implement the chosen use case
    using the acquired skills and knowledge. Analyze the results and present findings in a report

    Text Books:
    1. THE HUNDRED-PAGE MACHINE LEARNING BOOK by ANDRIY BURKOV, NIL

    References:
    1. MACHINE LEARNING by S SRIDHAR, M VIJAYALAKSHMI, OXFORD UNIVERSITY PRESS

    Session 2023-24 Page:2/2

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy