Posts

ML Exam Prep - Sagemaker AI

Image
  ML Associate Exam Prep  Sagemaker AI SageMaker  AI  is the “heart” of the MLA-C01 certification The majority of exam questions will have to do with SageMaker, and knowing it inside and out will be essential to do well in the exam. It is important to understand and discern between SageMaker Processing, SageMaker Training, and SageMaker Hosting, which all cover different aspects of the end-to-end ML process. These notes first cover generic ML knowledge and concepts, and then their implementation in AWS (usually involving SageMaker and other AWS services). Some open-source Apache services like Hadoop or Spark are also covered, since they are also popular in ML environments and are well supported in AWS It is a good idea to review the high-level overview of SageMaker that was done in the foundational AIF-C01 certification. MLA-C01 builds on top of that knowledge. Intro to SageMaker AI AWS service that can handle the whole E2E process in ML E2E ML process ...
Post a Comment
Read more

Dapper with C#

Dapper with C#    Dapper is best used when you prioritize max performance and total control over SQL. While Entity Framework (EF) Core is a feature-rich Object-Relational Mapper (ORM) designed for productivity, Dapper is a "micro-ORM" that provides a thin, high-speed layer over ADO.NET. Key Reasons to Choose Dapper Over EF Core Superior Performance:  Dapper has minimal overhead because it does not perform change tracking, LINQ-to-SQL translation, or complex entity materialization. Benchmarks often show Dapper is significantly faster, especially for large datasets or high-frequency read operations. Full SQL Control:  You write raw SQL directly, giving you complete flexibility to use database-specific features like  Common Table Expressions (CTEs) , window functions, or specialized joins that might be difficult to express in LINQ. Reduced Memory Allocation:  Because it lacks the heavy state-management infrastructure of EF Core, Dapper typically consumes less ...
Post a Comment
Read more

ML Exam - Transformers and LLMs

  ML Associate Exam Prep  Transformers and LLMs Basic Concepts - Tokens and Embeddings Tokens = numerical representations of words or parts of words A word can consist of 1+ tokens Punctuation signs (. “ ,) are also usually tokens Words/tokens can be loosely thought as the same , although strictly speaking they're obviously different Embeddings = mathematical representations (vectors) that encode the “meaning” of a token Evolution of the Transformer Architecture 1. RNNs and LSTMs    Recurrent Neural Networks (RNNs) are AI models designed for sequential data - like text or time series - by using internal memory to process inputs in order.     Long Short-Term Memory (LSTM) networks are a specialized, advanced type of RNN created to solve the "vanishing gradient" problem, allowing them to learn long-term dependencies that standard RNNs forget.    RNNs and LSTMs are obsolete with Transformers for many NLP tasks, though they remain rele...
Post a Comment
Read more

Ground Zero Agile Project

Ground Zero Agile Project   So you have chosen to do a project the Agile way and read the Agile Manifesto, what to do?  What is the plan?  So this article is a proposed "Ground Zero" project.   All Agile projects must be: 1) deployable to the target computer system to demo, 2) a manifest to make it deployable but flexible, 3) the developer team is ready to go with working (and proficient) with their programming language (if not, then we need to train them) and code generator or AI, 4) there is a given source control app governing CI/CD, 5) and that the user stories have been done for the first sprint.   All Agile projects for software vendors, need to have a common company app (for the company's eventual suite of products) that: 1) does admin piece (where first installer sets up the administrator user and some other users, 2) shows some license screen, 3) shows the common expected user interface layout (so team gets to practice with this.)    Suggestio...
Post a Comment
Read more

AI Exam 5 - AI Aspects

AI Practitioner Exam Prep -  Aspects of AI Cost Considerations   Cost factors are responsiveness and availability, redundancy and regional coverage, performance, token-based pricing, provisioned throughput, and refining your custom models. Responsible AI Aspects: controllability, explainability, fairness, governance, interpretability\transparency, privacy\security (theft and exposure risk), safety, and veracity\robustness.   Business Benefits: trust, regulatory complain, mitigate risks, competitive advantage, improved decision making, and improved products.    Model Selection: a)  Narrow the use case to tune your model to your use case.  Ex: favor recall or precision , b) pick by performance with some test data sets,  c) responsible agency, d) environmental reasons, e) economical reasons.   Dataset Prep: want  balanced dataset  so  inclusive and diverse  in data collection, curating by 1) preprocessing, 2) augmentat...
Post a Comment
Read more

AI Exam 4 - Products

AI Practitioner Exam Prep -  Products Abbreviations KMS  =  Amazon   Key Mgmt Service  product;  A2I =  Augmented AI Developer Products (in ML frameworks layer) SageMaker   AI  =  IDE  plugin that is  fully managed service that automates ML lifecycle ( from data prep to production) with " no-code" environment and handles infrastructure to streamline building, tuning , and deploying models.  Capabilities: Predictive analytics, computer vision, NLP, and fraud detection. Operations: Features auto-training and integrated logging. Security & Data: Secured via IAM ; integrates with S3 (storage), Lambda (triggers),  CloudWatch ( monitoring)  and API Gateway (endpoints) .     Auto Model Tuning feature exists on Sagemaker.     Auto Pilot = uses Clarify to show how ML models could make  predictions. uses  SHAP values. Auto finds the  best hyperparameters.     Canvas...
Post a Comment
Read more

AI Exam Prep - 3E Metrics

  AI Practitioner Exam Prep -  Metrics Text Metric Terms BERT  =  Text. s cores  semantic similarity  (using cosine) between two sentences . Good for text generation, summarization, translation, and filling in missing words.  think brainy Bert.  Counts: words that mean the same. BLEU  =  Text. S cores exact word translation did against human translated sample(s).  Counts: exact words only.  think  t ranslation because it is foreign spelling of blue.  METEOR  =  Text. e valuates by exact matches, stemmed matches, and synonyms. focus on both recall and precision.  think poetry meter. Counts: s ynonyms and word order. Perplexity  =  Text. calcs  how well probability model predicts a sample token, not the text quality.  Counts: Confusion level of model of its prediction. ROUGE  =  Text.  Uses F1, precision, and recall versus a reference text.  Good for...
Post a Comment
Read more