Python Data Science Essentials Third Edition

📓 Book

Managing Machine Learning Projects
Автор: Simon Thompson

Non-Adversarial Learning: Vector-Quantized Common Latent Space for Multi-Sequence MRI


Publication date: 03 Jul 2024

Topic: Contrastive Learning

Paper: https://arxiv.org/pdf/2407.02911v1.pdf

GitHub: https://github.com/fiy2w/mri_seq2seq

Description:

We propose a generative model that compresses discrete representations of each sequence to estimate the Gaussian distribution of vector-quantized common (VQC) latent space between multiple sequences. Moreover, we improve the latent space consistency with contrastive learning and increase model stability by domain augmentation.

OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images


Publication date: IEEE Transactions on Geoscience and Remote Sensing 2024

Topic: Object detection

Paper: https://arxiv.org/pdf/2409.19648v1.pdf

GitHub: https://github.com/wokaikaixinxin/OrientedFormer

Description:

In this paper, we propose an end-to-end transformer-based oriented object detector, consisting of three dedicated modules to address these issues. First, Gaussian positional encoding is proposed to encode the angle, position, and size of oriented boxes using Gaussian distributions. Second, Wasserstein self-attention is proposed to introduce geometric relations and facilitate interaction between content and positional queries by utilizing Gaussian Wasserstein distance scores. Third, oriented cross-attention is proposed to align values and positional queries by rotating sampling points around the positional query according to their angles.

OpenAI Snags Chat_com

OpenAI has acquired the premium domain name Chat.com and is now redirecting it to ChatGPT.

* Makes ChatGPT more accessible with an easy-to-remember address.

Previously owned by HubSpot co-founder Dharmesh Shah

Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning


Publication date: 16 Oct 2024

Topic: Representation Learning

Paper: https://arxiv.org/pdf/2410.12657v1.pdf

GitHub: https://github.com/junxia97/simgrace

Description:

In this paper, we propose a novel method, Explanation-Preserving Augmentation (EPA), that leverages graph explanation techniques for generating augmented graphs that can bridge the gap between semantics-preservation and data-perturbation. EPA first uses a small number of labels to train a graph explainer to infer sub-structures (explanations) that are most relevant to a graph's semantics. These explanations are then used to generate semantics-preserving augmentations for self-supervised GRL, namely EPA-GRL. We demonstrate theoretically, using an analytical example, and through extensive experiments on a variety of benchmark datasets that EPA-GRL outperforms the state-of-the-art (SOTA) GRL methods, which are built upon semantics-agnostic data augmentations.

Meta Unveils New Tools for Advancing Robotics and Machine Intelligence😳

Meta's FAIR Lab is pushing the frontier of robotics with a suite of innovative tools aimed at advancing machine intelligence. Highlights include Meta Sparsh, the first versatile encoder for vision-based tactile sensing, adaptable across different sensors and tasks. Meta Digit 360, an artificial fingertip, offers precise touch data with human-level sensitivity, while Meta Digit Plexus streamlines data collection and control with a unified cable platform.

A short history of the emoji

One of the most effective ways to learn machine learning is by getting hands-on experience and building something yourself.

While finding inspiration can be challenging, exploring projects by others can open your eyes to the endless possibilities. 💡

The projects I am sharing are perfect for those new to machine learning and curious about its potential.