CURRICULUM

• Take your AI and Machine Learning skills to a new level!

• 5x days of intense, quality and fun learning.

• Aesthetically pleasing in print, digital and audio formats.

• Horizontal learning experience for more immersive study.

• 80+ Hours of learning rich, targeted and in-depth content without the fluff.

• Content, demos, labs and exercises prepared by our professionals, at every stage and topic of the course for beginners and advanced levels.

• Official and only learning courseware, for the C|AAINE™ online and on-site course.

Course Formats

• Digital Courseware Book: for instructor-led courses (online or on-site) and for eLearning platform.

• Print Courseware Book: for instructor-led courses (online or on-site) only and on-demand.

• Course delivery:

  • Online self-paced self-study (via our Obi.Academy eLearning audio/visual platform)

  • Online course delivery (via our Obi.Academy eLearning audio/visual platform)

  • Onsite course delivery (via our partners Startel B.V. in the Netherlands and South Africa)

Course Delivery:

The Certified Applied Artificial Intelligence and Natural Language Processing Expert (C|AAINE™) course is available online as a self-paced self-study course or as an instructor-led online and onsite, with our approved training partners (ATPs) in the UK and Europe. Obipixel Ltd is actively in discussions with potential partners in the USA, Africa and Asia. To enquire about becoming an approved training provider and affiliate or a learner/attendee on our courses with our partners with Obi.Academy please contact us for further details.

Course Breakdown

Day 1 – Foundations of NLP and Generative AI

Module 1: Introduction to Generative AI and NLP Techniques

• 1.1 What is Generative AI?

• 1.2 Core NLP Concepts: Tokens, Embeddings, Transformers, Attention

• 1.3 Setting Up Tools: LLaMA 3, Mistral, APIs, Platforms

• 1.4 Preprocessing and Normalisation Techniques

Module 2: Foundational NLP with Pre-trained Models

• 2.1 Tokenisation, Embeddings

• 2.2 RNNs, Word2Vec, GloVe

• 2.3 Handling Missing/Noisy Data

• 2.4 Feature Engineering (TF-IDF)

Labs:

• Lab 0: LLaMA 3 Transformers

• Lab 1: BoW and TF-IDF

• Lab 2: Working with Word2Vec & GloVe Embeddings & Semantics

• Lab 7: Understanding RNNs for Sequential Data

• Lab 8: Exploring Word2Vec Embeddings for semantic relationships

• Lab 9: Understanding GloVe Embeddings for semantic relationships

Day 2 – Fine-Tuning and Customisation of AI Models

Module 3: Fine-Tuning LLMs

• 3.1 What is Advanced Fine-Tuning?

• 3.2 Instruction-Tuning

• 3.3 Domain Adaptation

• 3.4 Parameter-Efficient Fine-Tuning

Module 4: Applied Prompt Engineering

• 4.1 Prompt Engineering for Custom Tasks

• 4.2 Chain-of-Thought Reasoning

• 4.3 Zero-shot, Few-shot, Multi-shot Prompts

• 4.4 Evaluation and Deployment

Labs:

• Lab 3: Sentiment Analysis using NLP and LLMs

• Lab 4: Text Summarisation with LLMs

• Lab 5: Fine-Tuning an LLM for Domain-Specific Tasks

• Lab 10A: Implementing Attention Mechanisms with Seq2Seq

• Lab 10B: Working with Python and Split-Flow to Train Your Local LLM (Ollama)

• Lab 10C: Baking Unsupervised Data into a Local LLM using Python

Day 3 – Advanced Applications: NER, Multilingual, Multimodal

Module 5: Named Entity Recognition (NER)

• 5.1 What is Entity Recognition?

• 5.2 NER Models

• 5.3 Applications of Entity Recognition

• 5.4 Steps, Challenges & Ethics

Module 6: Translation & Multilingual Summarisation

• 6.1 What is Machine Translation?

• 6.2 Challenges in Translation

• 6.3 Multilingual Summarisation

• 6.4 Translation Pipelines & Real-World Applications

Module 7: Multimodal Content Generation

• 7.1 What is Multimodal Generation?

• 7.2 Multimodal Models (Gemini, BLIP, Grok)

• 7.3 Applications in Industry

• 7.4 Pipelines and Ethical Challenges

Labs:

• Lab 6: Entity Recognition Using NLP (Python & C#)

• Lab 11: Multilingual Translation with LLMs (GPT‑5.2 & Gemini)

• Lab 12: Multilingual Summarisation with LLMs (GPT-5.2 & Gemini)

• Lab 13: Summarisation with LLaMA 3, and Comparing Against Traditional Methods (TF-IDF)

• Lab 14: Fine-Tune LLaMA 3 for Translation, Then Evaluate with Native-Speaker Rubrics (Local, Ollama)

• Lab 15: Fine Tuning LLaMA3-Domain Multimodal-Python and C#

Day 4 – Deployment and Dashboarding

Module 8: Model Deployment (Web, Python, C#)

• 8.1 What is Model Deployment?

• 8.2 Deployment Workflow

• 8.3 Web, Python, and C# Integrations

• 8.4 Case Studies & Ethical Considerations

Module 9: Building Multimodal Dashboards

• 9.1 What are Multimodal Dashboards?

• 9.2 Components and Frameworks (Streamlit, Dash, Blazor)

• 9.3 Connecting LLMs to Dashboards

• 9.4 Use Cases and Best Practices

Labs:

• Lab 16: Mistral Content Generation-Python and C#

• Lab 17: Calling a Pre-trained LLaMA 3 Model via Hugging Face API (C# and Python)

• Lab 18: Attention Mechanisms in Mistral (Token-Level Visualisation)

• Lab 19: Structured API Prompt Engineering and Response Processing

• Lab 20: Developing a Summarisation API Consumer with HTTP Response

Day 5 – Pipelines, Real-Time Systems, and Final Integration

Module 10: Comprehensive Pipeline Implementation

• 10.1 What is a Comprehensive Pipeline?

• 10.2 Building NLP Pipelines

• 10.3 Multimodal and Real-Time Pipelines

• 10.4 Deployment and Monitoring

Module 11: Deploying Models to Applications (Web, Python, C#)

• 11.1 Deployment Workflow

• 11.2 Web App Integration

• 11.3 Python & C# API Integration

• 11.4 Case Studies

Module 12: Building Multimodal Dashboards

• 12.1 Components of a Multimodal Dashboard

• 12.2 Frameworks for Development

• 12.3 Connecting Models to Dashboards

• 12.4 Sector-specific Use Cases

Module 13: Full Pipeline Case Studies

• 13.1 Real-Time Threat Detection (Cybersecurity)

• 13.2 Financial Forecasting Pipeline

• 13.3 Monitoring, Scaling and Evaluation

Labs:

• Lab 21: Designing a Multimodal Dashboard Wireframe

• Lab 22: Streamlit Dashboard with LLaMA 3 via Ollama (Local Summarisation)

• Lab 23: Multimodal Input-Output with Claude and Gemini

• Lab 24: Banking Dashboard-GPT-Mistral-Ollama

• Lab 25: Real-Time Social Listening Dashboard with Grok (xAI) + X (Twitter)

• Lab 26: End-to-End Multimodal Dashboard

• Lab 27: End-to-End NLP Pipeline-Finance

• Lab 28: Real Time Threat Detection Pipeline-Cybersecurity

Examination

The examination has been strategically developed in-house and is only offered by Obipixel Ltd at Obi.Academy. This ensures the best quality possible and the most intensive and rigorous testing of our students, without compromise. Many examination providers do not adhere to this focus, and thus examination questioning is diluted and often not even relevant. Once our students have learnt their subject matter using the Certified Applied Artificial Intelligence and Natural Language Processing Expert (C|AAINE™) Academy Guide and they have chosen to attend our online or onsite courses, they will be tested correctly and fairly without worrying about content that is not relevant and not meant to be in their examination, which is such a systemic problem in today’s examinations across so many vendor products.

Duration: 4 hours
Pass Mark: 75%
Proctoring: Exam is proctored online with webcam and audio monitoring.
Questions: 150 (from a pool of 1000 randomly rotated questions in a blockchain for absolute control).
Exam Voucher: Available for order and provided by Obi.Academy and any Approved Training Provider. Vouchers are available at £200/voucher/student.
Achievement: Certification (for life), Certificate and Digital Badge.