DeText: A Deep Neural Text Understanding Framework

DeText can be applied to many tasks, including search & recommendation ranking, multi-class classification and query understanding tasks.

Github: https://github.com/linkedin/detext

Paper: https://arxiv.org/abs/2008.02460v1

@ai_machinelearning_big_data

📗 Forward from the 'Deep Learning for Coders' Book

Post: https://www.fast.ai/2020/08/20/soumith-forward/

Free Book in Jupiter: https://github.com/fastai/fastbook/blob/master/01_intro.ipynb

Github: https://github.com/fastai/fastbook

@ai_machinelearning_big_data

Top2Vec

Top2Vec is an algorithm for topic modeling and semantic search. It automatically detects topics present in text and generates jointly embedded topic, document and word vectors.

Github: https://github.com/ddangelov/Top2Vec

Paper: https://arxiv.org/abs/2008.09470v1

Doc2vec: https://radimrehurek.com/gensim/models/doc2vec.html

AN AMAZING COMPUTER VISION PROJECT
A sneak peek into the self-driven cars 🔥🔝💯✅



https://data-flair.training/blogs/road-lane-line-detection/

DeepMind's Traffic Prediction with Advanced Graph Neural Networks

A new blog post by DeepMind has been released recently that describes how you can apply GNN for travel time predictions. There are not many details about the model itself (which makes me wonder if deep net trained across all supersegments would suffice), but there are curious details about training.

1. As the road network is huge I suppose, they use sampling sampling of subgraphs in proportion to traffic density. This should be similar to GraphSAGE-like approaches.

2. Sampled subgraphs can vary a lot in a single batch. So they use RL to select subgraph properly. I guess it's some form of imitation learning that selects graphs in a batch based on some objective value.

3. They use MetaGradients algorithm to select a learning rate, which was previously used to parametrize returns in RL. I guess it parametrizes learning rate instead in this blog post.

https://dafriedman97.github.io/mlbook/content/table_of_contents.html

And The list of Most Updated and Free Artificial Intelligence, Machine Learning, Data Science, Deep Learning, Mathematics, Python Programming Resources. (Last Update: Sept 9, 2020):

https://www.marktechpost.com/free-resources/?fbclid=IwAR0hc2qkxPMXhQGzsg07ffgFecRr01tSCRqlhb_XMR6PjPt1KNdy68cLy9w

St Petersburg, Russia, 75 year after Victory in WWII celebration. Drone show

​​pytorch lightning bolts
from linear, logistic regression on tpu-s to pre-trained gan-s

plb – is a collection of pytorch lightning implementations of popular models that are well tested and optimized for speed on multiple gpu-s and tpu-s

it is a new community built dl research and production toolbox, featuring a collection of well established and sota models and components, pre-trained weights, callbacks, loss functions, data sets, and data modules

everything is implemented in lightning and tested benchmarked, documented, and works on cpu-s, tpu-s, gpu-s, and 16-bit precision

more u can read at the blog post


github: https://github.com/PyTorchLightning/pytorch-lightning-bolts

#pytorchlightning #bolts #multiple

TensorBoard is a tool for providing the measurements and visualizations needed during the machine learning workflow. It enables tracking experiment metrics like loss and accuracy, visualizing the model graph, projecting embeddings to a lower dimensional space, and much more.

#ts, #python, #tensorflow, #machine, #learning, #visualization

Understanding the Role of Individual Units in a Deep Neural Network

Examine two types of networks that contain interpretable units: networks trained to classify images of scenes, and networks trained to synthesize images of scenes.

https://dissect.csail.mit.edu/

Github: https://github.com/davidbau/dissect

Website: https://www.pnas.org/content/early/2020/08/31/1907375117

Paper: https://arxiv.org/pdf/2009.05041.pdf

Silero Speech-To-Text Models V1 Released

We are proud to announce that we have released our high-quality (i.e. on par with premium Google models) speech-to-text Models for the following languages:

- English
- German
- Spanish

Why this is a big deal:

- STT Research is typically focused on huge compute budgets
- Pre-trained models and recipes did not generalize well, were difficult to use even as-is, relied on obsolete tech
- Until now STT community lacked easy to use high quality production grade STT models

How we solve it:

- We publish a set of pre-trained high-quality models for popular languages
- Our models are embarrassingly easy to use
- Our models are fast and can be run on commodity hardware

Even if you do not work with STT, please give us a star / share!

Links

- https://github.com/snakers4/silero-models