Learn AI Together — Towards AI Community Newsletter #23

Author(s): Towards AI Editorial Team

Originally published on Towards AI.

Good morning, AI enthusiasts!

One of the major roadblocks for those diving into AI now is not knowing where to start. I tried to make that part easier with this GitHub Repository I created for those without any background in the field: a complete guide to start and improve in ML and AI. If you dream of working with large language models (LLMs) and have a good programming background, I also created this one for you: Start with Large Language Models (LLMs) — Become an expert for free!

If you enjoy reading the above guides, let us know! We are working on something similar but at a much larger scale. Currently, it is an underground project that we are perfecting, but if you are curious about building AI applications, this will be pretty useful for you. Watch this space for the updates!

Now, for this week’s issue, thanks to the combined efforts of the community, we have some new research and collaborations for you and a meme that is either funny or existential!

What’s AI Weekly

Since I’ve been involved in building many LLM and RAG-based applications and courses, I wanted to find the best, cheapest, and easiest way possible to build an RAG chatbot hosted on Discord, which I use daily. This week, I will show you how I got a chatbot running in under 10 minutes (no exaggeration) that can answer any question about your data, which can be a class textbook, company data, or anything else you want. The bot can use your OpenAI key to leverage GPT models, as I’ll do, or open source models with any HuggingFace hosted models. As a bonus, the bot’s Discord release is even included in this 10-minute deployment.

Check out the video here to build your own chatbot!

-Louis-François Bouchard, Towards AI Co-founder & Head of Community

Learn AI Together Community section!

Featured Community post from the Discord

Frikyfriks just wrote their first paper on exploring the creative process in the human brain and comparing it to the SOTA text-to-image architectures. Read the paper here and support a fellow community member. If you have feedback on how to improve it, share it in the thread!

AI poll of the week!

Join the discussion on Discord.

Collaboration Opportunities

The Learn AI Together Discord community is flooding with collaboration opportunities. If you are excited to dive into applied AI, want a study partner, or even want to find a partner for your passion project, join the collaboration channel! Keep an eye on this section, too — we share cool opportunities every week!

1. Apen5595 is looking for a collaborator for his open-source project named Project Zephyrine. It is a personal AI Assistant that utilizes local processes with the Adelaide paradigm. If you can contribute to this, connect with him in the thread!
2. Edoardo022 is working on an open-source research paper. The hypothesis is centered on whether we can predict the success or failure of an IPO using machine learning. If you like the world of research and want to contribute, reach out to them in the thread!
3. Fortbonnitar has developed a plugin for Unreal Engine that allows communication between a game and a Python script to send and receive information to and from a simulation. If you would like to collaborate on a test of this system, contact them in the thread!

Meme of the week!

Meme shared by ghost_in_the_machine

TAI Curated section

Article of the week

Understanding Convolutional Neural Network (CNN) — A Guide to Visual Recognition in the AI Era by Vincent Liu

YOLO has long been one of the first go-to models for object detection tasks. It’s fast and accurate. This article will elaborate on the five loss functions used in YOLOv8. It also discusses the default loss functions configured in the YOLOv8 repository, representative parameters, etc.

Our must-read articles

1. Best Resources to Learn & Understand Evaluating LLMs by Youssef Hosni

Large language models (LLMs) are gaining popularity in academia and industry owing to their unprecedented performance in various applications. This article presents a comprehensive set of resources that will help you understand LLM evaluation, starting with what to evaluate, where to evaluate, and how to evaluate.

2. Understanding Convolutional Neural Network (CNN) — A Guide to Visual Recognition in the AI Era by Sanket Rajaram

This article will help you understand the application of conventional artificial neural networks to visual recognition problems. You will also understand the basics of convolutional neural networks, different image processing strategies for feature generation, and dimensionality reduction techniques for improving computational complexity.

3. 7 Best Machine Learning Workflow and Pipeline Orchestration Tools by Eryk Lewinson

This article briefly describes ML workflows and pipelines. It also provides an overview of the best tools currently available. Some of these were developed by big tech companies such as Google, Netflix, and Airbnb. Hundreds of companies (tech and non-tech!) use each of these tools worldwide to streamline their data and ML pipelines.

If you are interested in publishing with Towards AI, check our guidelines and sign up. We will publish your work to our network if it meets our editorial policies and standards.

Think a friend would enjoy this too? Share the newsletter and let them join the conversation.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI