Timbo Smash

Read it, Smash it!

machine-learning

  • Smash some new AWS Certs for AI and ML

    Now that I’ve passed these exams, I wanted to share some thoughts from a security perspective, along with some general observations:AI1-C01: AWS Certified AI Practitioner (Beta) – PassedI was pleasantly surprised to see that security topics make up about 15% of the exam.– Covers general AWS security (IAM, CloudWatch, CloudTrail)– Focuses on Bedrock security– Guardrails Read more

  • The greate adventure of luna and the dreaded Data Drift Monster (fun story, to learn basic ML Algorithms). Created with Claudia

    Once upon a time, in the mystical land of Datopia, a young data scientist named Luna embarked on a perilous quest to save her kingdom from the dreaded Data Drift Monster. The monster had been wreaking havoc, causing models throughout the realm to underfit and overfit, leaving chaos in its wake. Luna began her journey Read more

  • More ML Models and Algorithms understanding using AWS AI and ML services as an example

    1. Amazon Rekognition: Image and Video Analysis 2. Amazon Comprehend: Natural Language Processing 3. Amazon Lex: Conversational Interfaces and Chatbots 4. Amazon Polly: Text-to-Speech Service 5. Amazon Translate: Language Translation 6. Amazon Transcribe: Speech-to-Text Service 7. Amazon Personalize: Real-Time Personalized Recommendations 8. Amazon Forecast: Time-Series Forecasting 9. Amazon Kendra: Intelligent Search Service 10. Amazon Textract: Read more

  • Exampe of a vector model training for say fruit pies, how it is used in training and how it structured in a database. Simple way to understand

    Example of a Vector Model Training for Fruit Pies To illustrate a vector model in the context of “fruit pies,” we’ll break down the process of training a vector model (such as a Word2Vec model) to represent different fruit pies in a way that captures their characteristics in a mathematical form (vectors). This approach is Read more

  • How can I use model explainability in AI with chatgpt to understand its desicions

    To understand the decisions made by ChatGPT and leverage model explainability in AI, there are several approaches you can use, especially when it comes to explainable AI (XAI) techniques. Here’s how you can apply model explainability in AI to ChatGPT-like models: 1. Token-Level Interpretability: Example: If you ask a question, you could analyze which words Read more

  • I smashed Wazuh back in the day

    I really liked wazuh, but with AI Wazuh is going ot have to step up the game. Great for small shops but next level for wazuh has to be AI and building models now. They are data rich and I could have some fun smashing some AI ideas with it. Read more

  • Now some sagemaker smashing Part 1 – TBD Getting data to use

    Here are some smashing resources to know: AWS SageMaker Documentation AWS Machine Learning Blog Amazon SageMaker Examples First you of course new an AWS account and setup S3 bucket with a data set. Take some time, but check out all the free data you can used among these. Next part we will get into creating Read more

  • Smashing some Text Feature Engineering

    Basics of Text Feature Engineering Techniques Text feature engineering involves transforming text data into numerical representations that can be used for machine learning models. Here are some common techniques: 1. Bag-of-Words (BoW) Concept: Represents text as a collection of words (or tokens), disregarding grammar and word order, but keeping multiplicity. Example: 2. N-Grams Concept: Extends Read more

  • Still smashing the AWS ML Ops Cert

    OK in the spirit of ML, I SMASHED jotted down some current notes and used Claude this time to take my notes and make a good write up: As an experienced AWS professional going through the AWS ML Ops certification training, I’ve noticed that some of the content feels outdated and doesn’t align with the Read more

  • Most a lot of ML terms so far from A Cloud Guru, not super smashing yet

    Read more