That's a wrap! If you are interested in any of these below topics: – Python – Data Science – Machine Learning – Data Analysis – LLMs – MLOps Find me → @Sumanth_077 I'm sharing daily content over here.
MACHINE LEARNING
-
Keypoint Feature Pyramid Network for 3D LiDAR Object Detection
By
–
📷 New Video Alert 📷https://t.co/WBwWd6SbVF
— Satya Mallick (@LearnOpenCV) 20 mai 2024
Watch our video on Learn OpenCV to dive into the implementation and training of the Keypoint Feature Pyramid Network for 3D LiDAR object detection.#ADAS #LiDAR #ObjectDetection #AutonomousDriving #Robotics pic.twitter.com/Q5PEV7g4zFNew Alert https://
youtu.be/qpUxmo6AYrY Watch our video on Learn OpenCV to dive into the implementation and training of the Keypoint Feature Pyramid Network for 3D LiDAR object detection. #ADAS #LiDAR #ObjectDetection #AutonomousDriving #Robotics -
Neural Networks, Big Data, and GPUs: Birth of Modern AI
By
–
This is a really good summary of how the breakthroughs in Neural Network (AlexNet), Big Data (ImageNet) and GPUs led to the birth of modern AI and computer vision. Thank you @Kseniase_ and your @TheTuringPost !
-
Naming Major AI and Computing Technologies at Google
By
–
It's nice to have good names for things. I'm proud to have named or been involved in naming a bunch of things at Google over the years, including: MapReduce
Bigtable
Spanner
TensorFlow
Tensor Processing Units (TPUs)
Pathways
Protocol Buffers
PaLM
Gemini -
Finetuning Models for Enhanced Long-Term Memory Capabilities
By
–
If they finetune the model to use to=bio, they could get a strong long-term memory out of the box
-
Comprehensive Study on Predicting Language Model Performance
By
–
Enjoyed this extremely comprehensive study on predicting language model performance http://
arxiv.org/abs/2405.10938. Found many insightful nuggets:
– In a single model family there usually aren't that many model sizes, which hinders predictive power. However, there are many model -
Data Decontamination and Generalization in Advanced Math Benchmarks
By
–
That's a valid point. The team tried hard to decontaminate the data. Also note that there's generalization into more challenging benchmarks such as HiddenMath and IMO-Bench.
-
Gemini 1.5 Pro Achieves 90% MATH Benchmark Milestone
By
–
Also astonishing to see how fast the field has advanced: Gemini 1.5 Pro was first to surpass the 90% mark on MATH (6.9% 3 years ago). For comparison, on ImageNet, it took us close to 10 years to achieve the same from AlexNet (40%) to Meta Pseudo Labels (90.2%, our work
-
Single First-Person Video Matches ImageNet for Vision Pretraining
By
–
Surprise: a single first-person video is as good as ImageNet for vision pretraining.