Data Phoenix

2021-12-24 10:00:05 Accelerating Inference Up to 6x Faster in PyTorch with Torch-TensorRT

Torch-TensorRT is the new integration of PyTorch with NVIDIA TensorRT, which accelerates the inference with one line of code. Learn how you can start using it today!

https://bit.ly/3eqGY2g Open / Comment

2021-12-23 16:00:04 Hello everyone!
We hope that your week is going well so far. Data Phoenix team wants to remind you about our weekly newsletter which is coming, as always, tomorrow! Fill in your email and get instant access to all the AI/ML goodies in one go. Looking forward to having you as one of our amazing subscribers!

https://bit.ly/3ElROBu Open / Comment

2021-12-23 10:00:03 End-to-End Referring Video Object Segmentation with Multimodal Transformers

This paper presents Multimodal Tracking Transformer (MTTR) that models the RVOS task as a sequence prediction problem. It simplifies the RVOS pipeline compared to existing methods.

https://bit.ly/3H85LVq Open / Comment

2021-12-22 10:00:05 Meta-Learning for Keyphrase Extraction

This article explores how to build a key phrase extractor that performs on in-domain data and in zero-shot scenarios where keyphrases need to be extracted from data with different distributions.

https://bit.ly/32sN3J6 Open / Comment

2021-12-21 10:00:04 GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training

GradInit is an automated and architecture agnostic method for initializing neural networks. It improves the stability of the original Transformer architecture for machine translation.

https://bit.ly/3pbIRX0 Open / Comment

2021-12-20 16:00:04 Visualizing the vanishing gradient problem

In this tutorial, you'll learn why the vanishing gradient problem exists, including its 101, do's and don'ts, and all about configurations of neural networks susceptible to vanishing gradient.

https://bit.ly/3yHl6sQ Open / Comment

2021-12-20 10:00:11 ​​ Happy Monday, friends! Data Phoenix team wishes you an amazing week! Today, we want to present to you Tamara McCleary

Tamara is the founder and CEO of a global social media marketing agency, Thulium. Currently, she’s a full-time graduate student at Harvard. As a research scientist at the Harvard Kennedy School, she studies science, technology, ethics, global economics, and public policy.

Tamara is interested in algorithmic governance, as well as the social, moral, ethical, and spiritual implications of genetic engineering. She prefers exploring various existential questions, and the future of religion in the world where life extension technologies, synthetic biology, artificial general intelligence, and our reliance on machines create a transhumanist and post-humanist existence.

She is also an advisor and crew member for the Proudly Human Off-World Projects, which simulates resource-constrained environments in search of solutions for those living off-world.

https://bit.ly/3skl5db Open / Comment

2021-12-19 16:00:04 NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

NÜWA is a unified multimodal pre-trained model that can generate new or manipulate existing visual data (i.e., images and videos) for various visual synthesis tasks.

https://bit.ly/33Id9s9 Open / Comment

2021-12-19 10:00:09 ​​ Hello friends!
We hope your Sunday is going great and you are ready for the upcoming week! But first things first, here's your weekly dose of positivity
https://bit.ly/3yMTe6L Open / Comment

2021-12-18 16:00:03 Learning Rates for Deep Learning Models

How can you make your deep learning models as effective as possible? In this article, you'll learn about the effects of a learning rate on the convergence and performance of DL models.

https://bit.ly/3e3Q1WV Open / Comment