machinelearning - CybAI news

20 Sep

Reconciling Conflicting Scaling Laws in Large Language Models

stp2y0 CommentsNewsai, beginners, coding, community, datascience, development, engineering, inclusive, machinelearning, software

This is a Plain English Papers summary of a research paper called Reconciling Conflicting Scaling Laws in Large Language Models. If you like these kinds of analysis, you should join AImodels.fyi or follow me on Twitter. Overview This paper reconciles two influential scaling laws in machine learning: the Kaplan scaling law and the Chinchilla scaling law. The Kaplan scaling law suggests that model performance scales as a power law with respect to model size and compute. The Chinchilla scaling law suggests that model performance scales more efficiently by tuning the compute and dataset size together. The paper aims to resolve…

08 Sep

Types of Machine Learning you must know!

stp2y0 CommentsNewsai, coding, community, deeplearning, development, engineering, inclusive, machinelearning, software, tutorial

There are 4 Major types of Machine Learning Supervised Learning Regression Classification Unsupervised Learning Clustering Dimensionality Reduction Anomaly Detection Association Semi Supervised Learning Reinforcement Learning Lets Explain one by one for a clear idea that what exactly they are about! Supervised Learning If we have a dataset with both input and output, our job is to understand the relationship between them. Then, we can use that understanding to predict the output for new input. This type of learning is called supervised machine learning. Example: Lets take 1000 Students Data. Now the ML model will create a mathematical link between the…

03 Sep

Training A Public FLUX Style LoRA — All Process Will Be Shared

stp2y0 CommentsNewsai, coding, community, development, engineering, inclusive, machinelearning, news, software, tutorial

I started training a public LoRA style (2 seperate training each on 4x A6000). Experimenting captions vs non-captions. So we will see which yields best results for style training on FLUX. Generated captions with multi-GPU batch Joycaption app. I am showing 5 examples of what Joycaption generates on FLUX dev. Left images are the original style images from the dataset. I used my multi-GPU Joycaption APP (used 8x A6000 for ultra fast captioning) : https://www.patreon.com/posts/110613301 I used my Gradio batch caption editor to edit some words and add activation token as ohwx 3d render : https://www.patreon.com/posts/108992085 The no caption dataset…

31 Aug

AWS AI Practitioner Exam: My Experience, Study Plan, and Resources

stp2y0 CommentsNewsai, aws, certification, coding, community, development, engineering, inclusive, machinelearning, software

The AWS Certified Artificial Intelligence Practitioner exam, currently in its beta phase, is designed for individuals eager to demonstrate their understanding of AI and machine learning concepts using AWS services. I recently took this beta exam to test my knowledge and contribute to the shaping of its final version. My motivation stemmed from a desire to stay ahead in the ever-evolving field of AI and enhance my career prospects in cloud-based AI solutions. In this article, I’ll share my experience with the beta exam, outline the preparation strategies that worked for me, and discuss the resources I found most beneficial.…

17 Aug

Building an Automated Customer Support System with NLP and Machine Learning

stp2y0 CommentsNewsautomation, coding, community, development, engineering, inclusive, machinelearning, nlp, software, tensorflow

Introduction In the age of digital transformation, providing efficient and effective customer support is crucial for businesses. Automating customer support using Natural Language Processing (NLP) and machine learning can significantly enhance the customer experience by providing instant responses and resolving common queries without human intervention. This article walks through the steps to build an automated customer support system, leveraging NLP to understand and respond to customer inquiries. Objectives Develop an NLP model to understand and process customer queries. Implement a machine learning algorithm to classify and route inquiries. Create a user-friendly interface for customers to interact with the support system.…

16 Aug

The activation functions in PyTorch (5)

stp2y0 CommentsNewsactivationfunction, coding, community, deeplearning, development, engineering, inclusive, machinelearning, pytorch, software

Buy Me a Coffee☕ *Memos: My post explains Step function, Identity and ReLU. My post explains Leaky ReLU, PReLU and FReLU. My post explains ELU, SELU and CELU. My post explains GELU, Mish, SiLU and Softplus. My post explains Vanishing Gradient Problem, Exploding Gradient Problem and Dying ReLU Problem. (1) Tanh: can convert an input value(x) to the output value between -1 and 1. *0 and 1 are exclusive. 's formula is y = (ex - e-x) / (ex + e-x). is also called Hyperbolic Tangent Function. is Tanh() in PyTorch. is used in: RNN(Recurrent Neural Network). *RNN in PyTorch.…

16 Aug

Machine Learning in Python Using Scikit-Learn: A Beginner’s Guide

stp2y0 CommentsNewscoding, community, datascience, development, engineering, inclusive, machinelearning, python, software

Are you interested in learning about machine learning using Python? Look no further than the Scikit-Learn library! This popular python library is designed for efficient data mining, analysis, and model building. In this guide, we will introduce you to the basics of Scikit-Learn and how you can start using it for your machine learning projects. What is Scikit-Learn?Scikit-Learn is a powerful and easy-to-use tool for data mining and analysis. It is built on top of other popular libraries like NumPy, SciPy, and Matplotlib. It is open-source and has a commercially available BSD license, making it accessible for anyone to use.…

09 Aug

Navigating the AI World: Lessons from My Internship at Mihira AI

stp2y0 CommentsNewsai, coding, community, development, engineering, inclusive, internship, machinelearning, software, techcommunity

Diving into AI isn’t just about crunching numbers or running algorithms—it’s about understanding complex systems, embracing challenges, and learning from every experience. During my internship at Mihira AI, I had the opportunity to do all of that, and more. In this post, I’ll share how my work on AI models shaped my skills, the importance of a supportive team, and why consistency is key in tech. Learning AI the Practical Way My workday typically wrapped up by 5 or 6 PM, but those hours were packed with learning. Whether I was fine-tuning models or solving complex problems, each task taught…

24 Jul

My first single file webpage I have no idea if this is right so pls give me some feedback

stp2y0 CommentsNewsbeginners, coding, community, development, devops, engineering, inclusive, machinelearning, react, software

<!DOCTYPE html> Barirah Uddin - Student Designer body { font-family: Arial, sans-serif; line-height: 1.6; margin: 0; padding: 0; background-color: #f0f0f0; color: #333; } <div class="highlight"><pre class="highlight plaintext"><code> .container { max-width: 800px; margin: auto; background-color: #fff; padding: 20px; border-radius: 8px; box-shadow: 0 0 10px rgba(0, 0, 0, 0.1); } header { text-align: center; margin-bottom: 30px; } header h1 { color: #333; font-size: 2.5em; margin-bottom: 10px; } header p { color: #666; font-size: 1.2em; } .section { margin-bottom: 40px; } .section h2 { border-bottom: 2px solid #333; padding-bottom: 5px; margin-bottom: 10px; } .section p { margin-top: 10px; } .portfolio-item { margin-bottom:…

20 Jul

Fine-tuning LLAMA 3 for Text Classification with Limited Resources

stp2y0 CommentsNewsai, coding, community, development, engineering, inclusive, machinelearning, python, software, tutorial

I recently needed to classify sentences for a particular use case at work. Remembering Jeremy Howard's Lesson 4: Getting started with NLP for absolute beginners, I first adapted his notebook to fine-tune DEBERTA. It worked, but not to my satisfaction, so I was curious what would happen if I used a LLM like LLAMA 3. The problem? Limited GPU resources. I only had access to a Tesla/Nvidia T4 instance. Research led me to QLORA. This tutorial on Fine tuning LLama 3 LLM for Text Classification of Stock Sentiment using QLoRA was particularly useful. To better understand the tutorial, I adapted…