AI, Python, Cognitive Neuroscience
3.78K subscribers
1.09K photos
46 videos
78 files
892 links
Download Telegram
In a paper published recently, researchers from MIT’s Computer Science & Artificial Intelligence Laboratory have proposed a method for learning a face from audio recordings of that person speaking.

In their architecture, researchers utilize facial recognition pre-trained models as well as a face decoder model which takes as an input a latent vector and outputs an image with a reconstruction.

Paper: https://lnkd.in/fiUBjqh

#machinelearning #deeplearning #speech2face

✴️ @AI_Python_EN
Avoiding Backtesting Overfitting by Covariance-Penalties: an empirical investigation of the ordinary and total least squares cases
Researchers: Adriano Koshiyama, Nick Firoozye
Paper: https://lnkd.in/fWtth8W
#artificialinteligence
#machineleaning #bigdata #machinelearning #deeplearning

✴️ @AI_Python_EN
Use of Artificial Intelligence Techniques / Applications in Cyber Defense
Researcher: Ensar Şeker
Paper: https://ow.ly/eqe450uukBx
#artificialinteligence #machineleaning #bigdata #machinelearning #deeplearning

✴️ @AI_Python_EN
Learning Compositional Neural Programs with Recursive Tree Search and Planning

Paper: https://ow.ly/dEaX50uukqv

#artificialinteligence #machineleaning #bigdata #machinelearning #deeplearning

✴️ @AI_Python_EN
Cracking open the black box of automated machine learning

#MachineLearning
https://bit.ly/2HN9ETC

✴️ @AI_Python_EN
The code for "Learning Undirected Posteriors by Backpropagation through MCMC" is released. I had lots of fun working on this. The paper comes with in-depth discussion of possible future works, ideal for summer interns😉
paper https://bit.ly/2XkcSDJ
code https://bit.ly/2WetVup

✴️ @AI_Python_EN
Bagdasaryan and Shmatikov find that training using private SGD increases error disparities between over and under-represented groups. They blame gradient clipping, which has a larger effect on data points less like the average. An interesting fairness/privacy tradeoff.
Differential Privacy Has Disparate Impact on Model Accuracy.
https://arxiv.org/abs/1905.12101

✴️ @AI_Python_EN
How Computers See Introduction to Convolutional Neural Networks

How do self-driving cars read street signs? How does Facebook automatically tag you in pictures? How does a computer achieve

✴️ @AI_Python_EN
Natural Language Inference with Deep Learning

Slides for the 2019 NAACL tutorial on Natural Language Inference with Deep Learning by Sam Bowman and Xiaodan Zhu: https://lnkd.in/eRicsNj

#artificialintelligence #deeplearning #naturallanguage

✴️ @AI_Python_EN
Tutorials on NLP from #NAACL2019. Thanks to the authors for sharing them with us to learn.

Deep Adversarial Learning for NLP - https://lnkd.in/fS9rCEv
Natural Language Inference with Deep Learning - https://lnkd.in/fk6MZea
Transfer Learning in NLP - https://lnkd.in/f6S8R6S

✴️ @AI_Python_EN
3DPalsyNet: A Facial Palsy Grading and Motion Recognition Framework using Fully 3D Convolutional Neural Networks
Researchers: Gary Storey, Richard Jiang, Shelagh Keogh, Ahmed Bouridane, Chang-Tsun Li
Paper: https://ow.ly/9aMK50uuW68
#artificialinteligence #machineleaning #bigdata #machinelearning #deeplearning

✴️ @AI_Python_EN
Empowering you to use machine learning to get valuable insights from data.

🔥 Implement basic ML algorithms and deep neural networks with PyTorch.
🖥 Run everything on the browser without any set up using Google Colab.
📦 Learn object-oriented ML to code for products, not just tutorials.

Github Link - https://lnkd.in/f8nu8UR

#datascience #data #dataanalysis #ml #machinelearning #deeplearning #ai #artificialintelligence

✴️ @AI_Python_EN
Sketch2code: Generating a website from a paper mockup
Researcher: Alex Robinson
Paper: https://ow.ly/zXHK50uuW3g
#artificialinteligence #machineleaning #bigdata #machinelearning #deeplearning
✴️ @AI_Python_EN
Media is too big
VIEW IN TELEGRAM
Roborace is the first racing competition for both autonomous and manual cars. The cars are all electric and have the same power specifications. Teams compete in developing the AI software.

They recently held an event in Spain:
https://lnkd.in/eDTAz8H

Roborace official site:
https://roborace.com/

#ArtificialIntelligence #MachineLearning #ComputerVision

✴️ @AI_Python_EN
EfficientNets: a family of more efficient & accurate image classification models. Found by architecture search and scaled up by one weird trick. Link: https://arxiv.org/abs/1905.11946 Github: https://bit.ly/30UojnC Blog: https://bit.ly/2JKY3qt
On the Fairness of Disentangled Representations

Locatello et al.: https://lnkd.in/d6DV-gX

#ArtificialIntelligence #DeepLearning #MachineLearning

✴️ @AI_Python_EN