Inventor Problem-Solver @Inventor_Solver

New things in the Machine Learning world from April's first week 🔥 github.com/osanseviero/ml…

Transformers-Recipe: 🧠 A study guide to learn about Transformers ⭐️ 1259 Author: @dair_ai #MachineLearning github.com/dair-ai/Transf…

GPT-4's vision API isn't public yet, but something better is here. Genmo: a creative & multimodal chatbot that not only takes image as input, but also generates and EDITs images and videos. Unlike Midjourney, Genmo is an *interactive* assistant able to genmo.ai…

Our team at Google Research is hiring student researcher for topics related to text-to-image synthesis and editing. Please write to me at [email protected] or drop me a DM if you are interested. (Retweets are welcomed!)

There's a lot of excitement about llama, which is non-commercial research licensed and needs separate instruction tuning. Why is there so little activity around flan-ul2 20B, which is tuned and openly licensed? yitay.net/blog/flan-ul2-…

Diffeomorphisms (warpings) are conveniently described in a Lagrangian way by advecting particles along a flow field. The Eulerian description corresponds to the advection equation. en.wikipedia.org/wiki/Advection en.wikipedia.org/wiki/Diffeomor… en.wikipedia.org/wiki/Lagrangia…

It may take a while but I think I can clone ChatGPT

DeepRob: Deep Learning for Robot Perception - University of Michigan, 2023 An ongoing class on neural network based approaches for robot perception. The class covers advanced topics in computer vision & emerging topics in deep robotic perception. Videos:youtube.com/playlist?list=…

Productive week! We recorded 5 new units of Deep Learning Fundamentals! And the new Units will start dropping mid-March: lightning.ai/pages/courses/… We'll cover code organization, computer vision, transformers, and performance tricks (mixed precision, multi-GPU paradigms & more!)

keyboard_arrow_left Previous keyboard_arrow_right Next

9 projects to learn Computer Vision: 1. Rock, Paper, Scissors 2. Classifying handwritten digits 3. Identifying house numbers 4. Tracking faces 5. Photo sketching 6. Blurring faces 7. Counting people 8. Detecting changes 9. Classifying traffic signs Deep Learning + OpenCV.

👉 Deep Learning for Computer Vision (DL4CV) Learn about modern methods for computer vision: CNN Advanced PyTorch Understanding Neural Networks RNN, Attention and ViTs Generative Models GPU Fundamentals 🔗 youtube.com/playlist?list=…

👉 Deep Learning for Computer Vision from Stanford This lecture collection is a deep dive into details of deep learning architectures with a focus on learning end-to-end models for image classification. 🔗 youtube.com/playlist?list=…

Here is the free version of the book Deep Learning for Coders with fastai and PyTorch that helps you with. → Deep Learning basics and Implementing the algorithms from scratch → Training models in computer vision, NLP and much more. Save this! github.com/fastai/fastbook

Deep Learning and Neural Networks have become the default approaches to Machine Learning in recent years. However, despite their spectacular success in certain domains (vision and NLP in particular), 1/5

Vision Transformers (ViTs) are a powerful deep learning architecture, but what’s the difference between ViT and a text-based transformer like BERT? Despite being applied in completely different domains, these models have only one major difference… 🧵[1/7]

Study Deep Learning for Free from MIT MIT's introductory course on deep learning methods with applications in computer vision, language, and more! Course Link: introtodeeplearning.com

Deep Learning Robotics Receives Patent for Revolutionary Computer Vision Technology ow.ly/npA050NqvA4

DeepSpeed + @berkeley_ai explore the effectiveness of MoE in scaling vision-language models, demonstrating its potential to achieve state-of-the-art performance on a range of benchmarks over dense models w. equivalent compute costs. arxiv.org/abs/2303.07226 More coming soon!

11. Advanced Machine learning Learn to apply deep learning & machine learning to practical problems. - Build & train models for vision, NLP, tabular data & more - Deploy your own models Join successful alumni at Google Brain, OpenAI & more! course.fast.ai

@flyosity You left out some parts in your timeline: ~2016: Attention mechanism in Seq2Seq models 2017: Google introduces Transformers 2019: OpenAI trains a Transformer (GPT-3) 2020: Google introduces Vision Transformer 2021: OpenAI introduces CLIP 2023: OpenAI trains a Transformer (GPT-4)