Bullsh*t that I and others have said about Neural ODEs
Original paper:
https://arxiv.org/abs/1806.07366
David's homepage:
https://www.cs.toronto.edu/~duvenaud/
https://www.youtube.com/watch?v=YZ-_E7A3V2w

join @ArtificialIntelligenceArticles

Paper: https://arxiv.org/abs/1912.05656

source code: https://github.com/mkocabas/VIBE

https://youtu.be/lAnYceBLsHc

join @ArtificialIntelligenceArticles

Pre-Debate Material
"The Consciousness Prior"
Yoshua Bengio : https://arxiv.org/abs/1709.08568
#DeepLearning #ArtificialIntelligence #AIDebate

GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
Engelcke et al.: https://arxiv.org/abs/1907.13052
#Artificialintelligence #DeepLearning #Robotics

My project, Mandarin Tone Trainer, is currently trending on Hacker News: https://news.ycombinator.com/item?id=21851495. I would love to get feedback on it and discuss how ML can help individuals to speak new languages.

🤩 Beyond Backpropagation

Border Pairs Method - more than 10 advantages over Backpropagation
Bipropagation - new algorithm for finding features - alternative for convolution
One Step Method - Deep learning algorithm for NN without strict layers what causes smaler number of neurons
https://www.researchgate.net/publication/322617800_New_Deep_Learning_Algorithms_beyond_Backpropagation_IBM_Developers_UnConference_2018_Zurich

If you are dabbling into ML/DL (deep learning)

Here is a post on how to structure your project code

with a informative quick infographic.

https://deeps.site/blog/2019/12/07/dl-project-structure/

Hope you save time by using the best practices :)

Bayesian Deep Learning Benchmarks

Oxford Applied and Theoretical Machine Learning Group : https://github.com/OATML/bdl-benchmarks

#Bayesian #Benchmark #DeepLearning

If you guys wanna get started with YOLO, take a look! YOLO is an extremely powerful object detection system.
https://becominghuman.ai/deep-learning-simplest-way-to-implement-yolo-an-extremely-powerful-object-detection-algorithm-9eae9d6191b7?gi=cc26e1486c94

Datasets: 23,000 NHS Doctor Jobs Postings
Download: https://www.kaggle.com/homelesssandwich/nhs-jobs

Learning Neural Causal Models from Unknown Interventions
Ke et al.: https://arxiv.org/abs/1910.01075
#AIDebate #MachineLearning #ArtificialIntelligence

Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning. https://arxiv.org/abs/1912.08881

https://www.kcl.ac.uk/news/novel-method-to-identify-tumours-with-ai-in-development-by-school-researchers

Artificial Intelligence algorithms to provide surgeons with greater accuracy to delineate tumours

What was your favorite paper of 2019?
Feel free to add your choice with the paper url link
rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch (https://arxiv.org/pdf/1909.01500.pdf)
SoftTriple Loss: Deep Metric Learning Without Triplet Sampling (https://arxiv.org/pdf/1909.05235.pdf)
Distributed Machine Learning on Mobile Devices: A Survey (https://arxiv.org/pdf/1909.08329v1.pdf)
Espresso: A Fast End-to-end Neural Speech Recognition Toolkit (https://arxiv.org/pdf/1909.08723v2.pdf)
MUSICNN: Pre-trained Convolutional Neural Networks for Music Audio Tagging (https://arxiv.org/pdf/1909.06654v1.pdf)
DeepPrivacy: A Generative Adversarial Network for Face Anonymization (https://arxiv.org/pdf/1909.04538v1.pdf)
BA-Net: Dense Bundle Adjustment Networks (https://openreview.net/pdf?id=B1gabhRcYX)
Momentum Contrast for Unsupervised Visual Representation Learning (https://arxiv.org/abs/1911.05722)

‘Cortex’: An open-source platform for deploying machine learning models as production web services
Github: https://github.com/cortexlabs/cortex
Tutorial: https://www.cortex.dev/iris-classifier
Examples: https://github.com/cortexlabs/cortex/tree/0.11/examples
https://www.marktechpost.com/2019/12/23/cortex-an-open-source-platform-for-deploying-machine-learning-models-as-production-web-services/

State of the art in deblurring and generating realistic high-resolution facial images
https://www.profillic.com/paper/arxiv:1912.10427

(An adversarial network comprising a generator and two discriminators is proposed)