Accelerating Federated Learning via Momentum Gradient Descent
Liu et al.: https://arxiv.org/abs/1910.03197
#ArtificialIntelligence #FederatedLearning #MachineLearning

TorchBeast: A PyTorch Platform for Distributed RL
Kuttler et al.: https://arxiv.org/abs/1910.03552
#DeepLearning #OpenAIGym #ReinforcementLearning

Spectral Inference Networks: Unifying Deep and Spectral Learning
Pfau et al. : https://arxiv.org/abs/1806.02215
#MachineLearning #DeepLearning #ArtificialIntelligence

Image Deduplicator
Tanuj Jain, Christopher Lennan, Zubin John and Dat Tran : https://github.com/idealo/imagededup
#DeepLearning #MachineLearning #Tensorflow

New book @ArtificialIntelligenceArticles

This book provides a thorough overview of the ongoing evolution in the application of artificial intelligence (AI) within healthcare and radiology, enabling readers to gain a deeper insight into the technological background of AI and the impacts of new and emerging technologies on medical imaging. After an introduction on game changers in radiology, such as deep learning technology, the technological evolution of AI in computing science and medical image computing is described, with explanation of basic principles and the types and subtypes of AI. Subsequent sections address the use of imaging biomarkers, the development and validation of AI applications, and various aspects and issues relating to the growing role of big data in radiology. Diverse real-life clinical applications of AI are then outlined for different body parts, demonstrating their ability to add value to daily radiology practices. The concluding section focuses on the impact of AI on radiology and the implications for radiologists, for example with respect to training. Written by radiologists and IT professionals, the book will be of high value for radiologists, medical/clinical physicists, IT specialists, and imaging informatics professionals.
@ArtificialIntelligenceArticles

Top book by stuart Russell

A leading artificial intelligence researcher lays out a new approach to AI that will enable us to coexist successfully with increasingly intelligent machines

In the popular imagination, superhuman artificial intelligence is an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Conflict between humans and machines is seen as inevitable and its outcome all too predictable.

In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage.

If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial.

In a 2014 editorial co-authored with Stephen Hawking, Russell wrote, "Success in creating AI would be the biggest event in human history. Unfortunately, it might also be the last." Solving the problem of control over AI is not just possible; it is the key that unlocks a future of unlimited promise.

https://www.amazon.com/Human-Compatible-Artificial-Intelligence-Problem-ebook/dp/B07N5J5FTS

Stuart Russell discusses his newest book on the AI Alignment Podcast, Human Compatible: Artificial Intelligence and the Problem of Control.
Stuart Russell discusses his newest book on the AI Alignment Podcast, Human Compatible: Artificial Intelligence and the Problem of Control.
https://futureoflife.org/2019/10/08/ai-alignment-podcast-human-compatible-artificial-intelligence-and-the-problem-of-control-with-stuart-russell/?cn-reloaded=1

Artificial Intelligence Could Be a $14 Trillion Boon to the Global Economy—If It Can Overcome These Obstacles
Bernhard Warner : https://fortune.com/2019/10/09/artificial-intelligence-14-trillion-boon-only-if-overcome-one-thing/amp/
#artificialintelligence #business #deeplearning

The videos and slides of yann lecun three Loeb Lectures in Physics at Harvard are available:

Videos: https://www.physics.harvard.edu/node/986
Slides:
- Colloquium: "The unreasonable effectiveness of deep learning" https://drive.google.com/open?id=1swvooYfqNeNfFYVNtfzWaMfKU-DID6Um
- lecture 2: "The energy-based formulation of learning", https://drive.google.com/open?id=117vpPLXuMy97a3-edg-NoQctc4OD7ZuT
lecture 3: "Intriguing connections between deep learning and physics", https://drive.google.com/open?id=13_ZT2rQG304B8zrOr74-c07lVAiGkbAL

Concise Machine Learning-Jonathan Richard Shewchuk (UC Berkeley)
Download: https://people.eecs.berkeley.edu/~jrs/papers/machlearn.pdf

A practical approach to machine learning.
https://practicalai.me/?fbclid=IwAR3WdnSAaESo1c8DOjG2p2MXZFfQ3xbM_wMZek4QXbv85yNwD32y6J1vyR0

Debate on Instrumental Convergence between Yann LeCun , Yoshua Bengio, Stuart Russell, Tony Zador , and More

https://www.lesswrong.com/posts/WxW6Gc6f2z3mzmqKs/debate-on-instrumental-convergence-between-lecun-russell
https://t.iss.one/ArtificialIntelligenceArticles

Free Book: Deep Learning and Computer Vision with CNNs
https://www.datasciencecentral.com/profiles/blogs/free-book-deep-learning-and-computer-vision-with-cnns

Transformers: State-of-the-art Natural Language Processing
Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Jamie Brew : https://arxiv.org/abs/1910.03771
#Transformers #NaturalLanguageProcessing #PyTorch #TensorFlow

Ph.D. Student or Postdoc in neuroscience

#University_of_Zurich
#Switzerland
https://jobs.uzh.ch/offene-stellen/phd-student-or-postdoc-in-neuroscience/cac36d3b-0ddc-48b2-9aaf-c92f25b315cd

Top 10 Python, AI and Machine Learning Open Source Projects

https://www.techleer.com/articles/501-top-10-python-ai-and-machine-learning-open-source-projects/

Visual example of loss function space for Object Detection on Pedestrian Detection Database with SSD300 model.

That's why training model can be tough, cause it's almost the same as climbing on the Everest and jumping into the Mariana Trench.

And that's why we are making course on Object Detection, to help understand such moments - subscribe https://upscri.be/vg7ilp