Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Applied AI: NLP, Computer Vision, Robot & GenAI Deployment
24 students

Applied AI: NLP, Computer Vision, Robot & GenAI Deployment

Master the core domains of applied AI—from NLP to computer vision and GenAI deployment—through real-world tools
Created byBanking and Finance School
Last updated 6/2025
English
English [Auto],

What you'll learn

  • Fundamentals and applications of NLP, including text classification and sentiment analysis
  • Computer vision techniques like object detection, segmentation, and image generation
  • Integration of AI with robotics, including reinforcement learning
  • Understanding, detecting, and managing hallucinations in generative AI
  • How to deploy generative AI models using cloud services and open-source tools
  • Best-in-class AI tools and platforms for real-world workflows
  • Ethical implications and real-life case studies in modern AI systems

Course content

6 sections • 47 lectures • 3h 52m total length

  • Basics of NLP4:04

    Discover the basics of natural language processing and how machines process, analyze, and generate language, including part of speech tagging, named entity recognition, and applications like translation and chatbots.

  • Text Preprocessing2:26

    Apply thorough text pre-processing to prepare raw text for NLP tasks. Use tokenization, lowercasing, punctuation removal, stop-word removal, stemming, lemmatization, and normalization to improve model performance.

  • Text Classification7:27

    Classify text by assigning predefined labels through supervised learning, enabling sentiment analysis, spam detection, topic modeling, and text summarization, using methods from Naive Bayes to neural networks.

  • Named Entity Recognition (NER)10:25

    Learn named entity recognition (NER) to identify and classify entities such as persons, organizations, locations, and dates within text, using preprocessing, feature extraction, and classification.

  • Sentiment Analysis7:23

    Learn how sentiment analysis uses natural language processing to classify text as positive, negative, or neutral. Apply preprocessing, feature extraction, sentiment lexicons, and machine learning models to feedback and reviews.

  • Language Generation Models (BERT, GPT)16:02

    Explore how language generation models like BERT and GPT use transformer architectures to process language. Learn key concepts like self-attention, positional encoding, encoder–decoder structures, pre-training, and fine-tuning.

Requirements

  • Basic understanding of programming (preferably in Python)
  • Familiarity with machine learning concepts is helpful but not mandatory
  • Willingness to experiment with AI tools and engage in hands-on projects
  • Internet access for working with cloud-based AI tools and APIs

Description

Course Introduction:

Artificial Intelligence has rapidly evolved from academic theory to real-world application. From powering chatbots to controlling autonomous robots, analyzing images, and generating synthetic content, AI is everywhere. This course is designed to give learners a robust, practical foundation in applied AI. We’ll explore six key areas: Natural Language Processing, Computer Vision, Robotics, Hallucination Management in Generative AI, Deployment Strategies, and a curated toolbox of AI tools. Whether you’re looking to enter the AI field, enhance your data science skills, or manage AI projects more effectively, this course offers practical insights, hands-on techniques, and modern best practices to help you succeed.

Section 1: Natural Language Processing (NLP)

We begin with Natural Language Processing—the field that enables machines to understand and generate human language. This section covers the Basics of NLP, followed by Text Preprocessing techniques like tokenization, stopword removal, and stemming. You'll explore Text Classification using supervised learning, delve into Named Entity Recognition (NER) for extracting structured data, and conduct Sentiment Analysis to gauge opinion from text. Finally, we’ll examine powerful Language Generation Models like BERT and GPT, highlighting how they’re transforming tasks like summarization, translation, and conversational AI.

Section 2: Computer Vision

In this section, you’ll explore how machines “see” and interpret visual data. Starting with Image Processing Basics, you’ll learn about filtering, noise reduction, and enhancement. Feature Extraction dives into edge detection and feature mapping techniques. You'll then explore Object Detection algorithms like YOLO and SSD, as well as Image Segmentation for pixel-level classification. Finally, Image Generation introduces GANs (Generative Adversarial Networks) and diffusion models, showcasing how AI can create realistic synthetic visuals.

Section 3: Robotics and AI

This section introduces how AI powers intelligent robotic systems. You’ll begin with the Basics of Robotics and learn about Key AI Technologies Used in Robotics, such as computer vision, path planning, and control systems. The lecture on AI in Robotics explores real-world use cases like warehouse automation and robotic surgery. Reinforcement Learning in Robotics demonstrates how robots learn from trial and error, making decisions in dynamic environments.

Section 4: Hallucination Management in GenAI

Generative AI can sometimes generate outputs that are factually incorrect or misleading—known as "hallucinations." This section starts with an Introduction and real-world Examples of Hallucinations. You’ll learn about the Causes, Types, and how to Detect and Evaluate Hallucinations using benchmarks and red-teaming strategies. Mitigation Strategies and Advanced Techniques cover fine-tuning, retrieval-augmented generation, and human-in-the-loop systems. Case Studies illustrate practical solutions, followed by a Quiz to reinforce understanding.

Section 5: Integration and Deployment of GenAI

This section provides a comprehensive guide to deploying generative AI systems in real-world environments. You’ll start with an Overview of Integration and the current Development Landscape. Learn about Key Considerations for Development, such as scalability, latency, and data privacy. The section includes Evaluating Deployment Methods and Vendors, featuring platforms like AWS Bedrock, Anthropic, and VLLM. Practical examples, case studies, and Hands-On Labs provide actionable skills. A fun recap lecture—Think You Know AI Deployments—tests your applied knowledge.

Section 6: AI Tools

This practical section introduces you to a suite of AI Tools across 11 focused lectures. Each session dives into one or more tools for tasks like data analysis, model development, deployment, and monitoring. From open-source libraries like TensorFlow and PyTorch to cutting-edge platforms like Hugging Face, Weights & Biases, and LangChain, you’ll gain a broad and useful toolkit that complements all areas of applied AI.

Course Conclusion:

You've now explored the key pillars of applied AI: from language and vision to robotics and responsible deployment. More than just theory, this course gives you practical workflows, tool mastery, and the ethical understanding required to implement AI successfully. Whether you're building a chatbot, analyzing satellite images, deploying GenAI models, or preventing AI hallucinations, you're ready to put your knowledge into action. AI is the future—this course ensures you’re not just watching it happen, but helping to shape it.

Who this course is for:

  • Aspiring AI professionals and data scientists
  • Software developers looking to integrate AI into products
  • Researchers and students seeking a hands-on AI foundation
  • Product managers and tech leads working on AI initiatives
  • Business and innovation leaders interested in deploying AI responsibly
  • Anyone eager to understand and work with practical AI tools in modern domains

Report abuse