Microsoft AI: Introduction to the Semantic Kernel SDK
Explore Microsoft's Semantic Kernel SDK for integrating LLMs with C#, Python, and Java. Learn to combine AI models with traditional programming for enhanced applications.
LLMOps: Comparison of OpenVino, ONNX, TensorRT, and PyTorch Inference
Explore model conversion to ONNX, OpenVino, and Tensor-RT formats for optimized CPU and GPU inference, comparing performance against native PyTorch.
MLOps: OpenVino Quantized Pipeline for Grammatical Error Correction
Build a grammar error correction model using OpenVino, combining Roberta-based error detection and Flan-T5 correction, with quantization for efficient CPU inference.
Computer Vision: OCR Tesseract in C# - Data Science and Machine Learning
Implement OCR using Tesseract library in C# for extracting text from images, enhancing your computer vision skills.
Object Detection with Faster R-CNN in C# Using ONNX on CPU
Implement object detection using Faster R-CNN in C# with ONNX format on CPU, leveraging machine learning for efficient image analysis.
Microsoft AI: Semantic Kernel C# SDK Chatting with Phi3 4k ONNX CPU - Machine Learning and Data Science
Develop a ChatBot using Phi3 Mini 4k Instruct ONNX model with Semantic Kernel C# SDK, integrating custom services for machine learning applications.
LLMOPs: Multimodal Prompting and Inference with Phi-3 Vision 128K Instruct on CPU - ONNX 4-Bit Quantization in C#
Explore multimodal prompting and CPU inference using Phi 3 Vision 128K Instruct, quantized to 4 bits in ONNX format, with C# implementation for efficient machine learning operations.
LLMOPs - Inference in CPU with Phi3 4k Instruct ONNX 4-bit Model Using C#
Explore CPU-based inference using 4-bit quantized Phi 3 4K Instruct in ONNX format with C#. Learn practical implementation for efficient machine learning deployment.
Prompt Engineering Techniques for Microsoft Phi3-mini 128k Instruct
Explore prompt engineering techniques for Microsoft Phi3-mini 128k Instruct, including zero-shot, few-shot, CoT, and RAG approaches.
LLMOps: Converting Video Classifier (ViViT) to ONNX and Inference on CPU
Convert a Video Vision Transformer to ONNX format and perform CPU inference, enhancing model portability and deployment flexibility for video classification tasks.
LLMOps: Fine-Tuning Video Classifier (ViViT) with Custom Data
Fine-tune a Video Vision Transformer (ViViT) using custom datasets. Learn to adapt Google's pretrained model for specialized video classification tasks.
Inside GPT - Large Language Models Demystified
Demystifying GPT algorithms: architecture, inner workings, and practical applications. Explore NLP fundamentals, train models, and learn to leverage ChatGPT and GPT4 for innovative solutions.
Adaptive Socio-Technical Systems with Architecture for Flow
Explore designing adaptive socio-technical systems using Team Topologies, Wardley Mapping, and Domain-Driven Design to optimize for fast flow of change in uncertain business environments.
Responsible AI in Practice - Building Ethical Machine Learning Systems
Explore best practices and open-source tools for implementing Responsible AI, ensuring ethical standards in machine learning applications across industries. Learn to align AI development with human-centric principles.
Accelerating Financial Processing and Reporting with Pre-Trained and Custom ML Models
Innovative approach using pre-trained and custom ML models to enhance financial data processing and reporting, streamlining workflows and improving efficiency in generating insights for the finance industry.
Secrets of Successful AI Projects - Strategies and Pitfalls
Unveiling AI project success: from concept to implementation. Learn key elements, strengths, limitations, and adoption stages. Gain insights on team organization and future trends for effective AI integration.
Secure LLM App Deployments - Strategies and Tactics
Discover strategies for enhancing LLM security using red-teaming techniques and Giskard's tools for automatic vulnerability detection in Generative AI applications.
Designing AI for Trust - Creating Value While Setting the Right Guardrails
Explore best practices for designing and deploying trusted AI solutions in critical sectors, focusing on human adoption, business alignment, risk management, and data curation challenges.
Applying Responsible AI with Open-Source Tools
Learn practical techniques for building safe, fair AI models using open-source tools. Tackle challenges in robustness, labeling errors, bias, and data leakage with hands-on examples for machine learning and NLP projects.
How to Reduce LLM Costs by 98% - Practical, Scalable Solutions
Discover advanced techniques to leverage LLMs cost-effectively. Learn strategies for using SLMs, LLM distillation, and prompt unit testing to overcome budget constraints while maintaining quality in GenAI projects.
From RAG to RICHES - Retrieval Interlaced with Sequence Generation
Innovative AI approach integrating retrieval into sequence generation, simplifying RAG systems. Adapts to new tasks through prompting, supports multi-hop retrievals, and excels in Open Domain Question Answering.