Top news of the week: 17.10.2019.

#AI #Tensorflow #AutoML #ML #PyTorch #ICMI #Masakhane #infoviz #Ada #sautiyetu

On Oct 17, 2019
@mat_kelcey shared
RT @hardmaru: Uncertainty Quantification in Deep Learning A nice overview blog post by @simonbachstein https://t.co/ZZExu1Vlau
Open

Uncertainty Quantification in Deep Learning

Teach your Deep Neural Network to be aware of its epistemic and aleatory uncertainty. Get a quantified confidence measure for your Deep Learning predictions.

On Oct 17, 2019
@mat_kelcey shared
RT @hardmaru: Uncertainty Quantification in Deep Learning A nice overview blog post by @simonbachstein https://t.co/ZZExu1Vlau
Open

Uncertainty Quantification in Deep Learning

Teach your Deep Neural Network to be aware of its epistemic and aleatory uncertainty. Get a quantified confidence measure for your Deep Learning predictions.

On Oct 10, 2019
@jeremyphoward shared
RT @ylecun: PyTorch 1.3 is live! Mobile device deployment, model quantization, named tensors, crypto, model interpretability, detectron2... https://t.co/yYQoJqbeUi https://t.co/XbQ08r2c8B
Open

PyTorch 1.3 adds mobile, privacy, quantization, and named tensors

The release of PyTorch 1.3 includes support for model deployment to mobile devices, quantization, and front-end improvements, like the ability to name tensors. We’re also launching tools ...

On Oct 15, 2019
@weballergy shared
RT @OpenAI: We've trained an AI system to solve the Rubik's Cube with a human-like robot hand. This is an unprecedented level of dexterity for a robot, and is hard even for humans to do. The system trains in an imperfect simulation and quickly adapts to reality: https://t.co/O04izt3KvO https://t.co/8lGhU2pPck
Open

Solving Rubik’s Cube with a Robot Hand

We've trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand.

On Oct 11, 2019
@ylecun shared
RT @gradientpub: The war between ML frameworks has raged on since the rebirth of deep learning. Who is winning? @cHHillee's data analysis shows clear trends: PyTorch is winning dramatically among researchers, while Tensorflow still dominates industry. #PyTorch #Tensorflow https://t.co/wgQQZTWcuG
Open

The State of Machine Learning Frameworks in 2019

Since deep learning regained prominence in 2012, many machine learning frameworks have clamored to become the new favorite among researchers and industry practitioners. From the early ...

On Oct 11, 2019
@petewarden shared
RT @thinkmariya: We’ve summarized the key ideas of the research paper “AutoML: the survey of the state-of-the-art” from the Hong Kong Baptist University. Check it out to know, on which tasks AutoML already outperforms human-designed models. #AI #AutoML #ML https://t.co/3Perrkg1zc
Open

What’s State Of The Art In AutoML in 2019?

Following the structure of the original paper, we’ll touch upon the available AutoML techniques, summarize existing approaches to Neural Architecture Search (NAS), provide you with the ...

On Oct 17, 2019
@mat_kelcey shared
RT @hardmaru: Uncertainty Quantification in Deep Learning A nice overview blog post by @simonbachstein https://t.co/ZZExu1Vlau
Open

Uncertainty Quantification in Deep Learning

Teach your Deep Neural Network to be aware of its epistemic and aleatory uncertainty. Get a quantified confidence measure for your Deep Learning predictions.

On Oct 10, 2019
@jeremyphoward shared
RT @ylecun: PyTorch 1.3 is live! Mobile device deployment, model quantization, named tensors, crypto, model interpretability, detectron2... https://t.co/yYQoJqbeUi https://t.co/XbQ08r2c8B
Open

PyTorch 1.3 adds mobile, privacy, quantization, and named tensors

The release of PyTorch 1.3 includes support for model deployment to mobile devices, quantization, and front-end improvements, like the ability to name tensors. We’re also launching tools ...

On Oct 15, 2019
@weballergy shared
RT @OpenAI: We've trained an AI system to solve the Rubik's Cube with a human-like robot hand. This is an unprecedented level of dexterity for a robot, and is hard even for humans to do. The system trains in an imperfect simulation and quickly adapts to reality: https://t.co/O04izt3KvO https://t.co/8lGhU2pPck
Open

Solving Rubik’s Cube with a Robot Hand

We've trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand.

On Oct 11, 2019
@ylecun shared
RT @gradientpub: The war between ML frameworks has raged on since the rebirth of deep learning. Who is winning? @cHHillee's data analysis shows clear trends: PyTorch is winning dramatically among researchers, while Tensorflow still dominates industry. #PyTorch #Tensorflow https://t.co/wgQQZTWcuG
Open

The State of Machine Learning Frameworks in 2019

Since deep learning regained prominence in 2012, many machine learning frameworks have clamored to become the new favorite among researchers and industry practitioners. From the early ...

On Oct 11, 2019
@petewarden shared
RT @thinkmariya: We’ve summarized the key ideas of the research paper “AutoML: the survey of the state-of-the-art” from the Hong Kong Baptist University. Check it out to know, on which tasks AutoML already outperforms human-designed models. #AI #AutoML #ML https://t.co/3Perrkg1zc
Open

What’s State Of The Art In AutoML in 2019?

Following the structure of the original paper, we’ll touch upon the available AutoML techniques, summarize existing approaches to Neural Architecture Search (NAS), provide you with the ...

On Oct 17, 2019
@mat_kelcey shared
RT @hardmaru: Uncertainty Quantification in Deep Learning A nice overview blog post by @simonbachstein https://t.co/ZZExu1Vlau
Open

Uncertainty Quantification in Deep Learning

Teach your Deep Neural Network to be aware of its epistemic and aleatory uncertainty. Get a quantified confidence measure for your Deep Learning predictions.

On Oct 10, 2019
@jeremyphoward shared
RT @ylecun: PyTorch 1.3 is live! Mobile device deployment, model quantization, named tensors, crypto, model interpretability, detectron2... https://t.co/yYQoJqbeUi https://t.co/XbQ08r2c8B
Open

PyTorch 1.3 adds mobile, privacy, quantization, and named tensors

The release of PyTorch 1.3 includes support for model deployment to mobile devices, quantization, and front-end improvements, like the ability to name tensors. We’re also launching tools ...

On Oct 15, 2019
@weballergy shared
RT @OpenAI: We've trained an AI system to solve the Rubik's Cube with a human-like robot hand. This is an unprecedented level of dexterity for a robot, and is hard even for humans to do. The system trains in an imperfect simulation and quickly adapts to reality: https://t.co/O04izt3KvO https://t.co/8lGhU2pPck
Open

Solving Rubik’s Cube with a Robot Hand

We've trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand.

On Oct 11, 2019
@ylecun shared
RT @gradientpub: The war between ML frameworks has raged on since the rebirth of deep learning. Who is winning? @cHHillee's data analysis shows clear trends: PyTorch is winning dramatically among researchers, while Tensorflow still dominates industry. #PyTorch #Tensorflow https://t.co/wgQQZTWcuG
Open

The State of Machine Learning Frameworks in 2019

Since deep learning regained prominence in 2012, many machine learning frameworks have clamored to become the new favorite among researchers and industry practitioners. From the early ...

On Oct 11, 2019
@petewarden shared
RT @thinkmariya: We’ve summarized the key ideas of the research paper “AutoML: the survey of the state-of-the-art” from the Hong Kong Baptist University. Check it out to know, on which tasks AutoML already outperforms human-designed models. #AI #AutoML #ML https://t.co/3Perrkg1zc
Open

What’s State Of The Art In AutoML in 2019?

Following the structure of the original paper, we’ll touch upon the available AutoML techniques, summarize existing approaches to Neural Architecture Search (NAS), provide you with the ...

On Oct 17, 2019
@mat_kelcey shared
RT @hardmaru: Uncertainty Quantification in Deep Learning A nice overview blog post by @simonbachstein https://t.co/ZZExu1Vlau
Open

Uncertainty Quantification in Deep Learning

Teach your Deep Neural Network to be aware of its epistemic and aleatory uncertainty. Get a quantified confidence measure for your Deep Learning predictions.

On Oct 10, 2019
@jeremyphoward shared
RT @ylecun: PyTorch 1.3 is live! Mobile device deployment, model quantization, named tensors, crypto, model interpretability, detectron2... https://t.co/yYQoJqbeUi https://t.co/XbQ08r2c8B
Open

PyTorch 1.3 adds mobile, privacy, quantization, and named tensors

The release of PyTorch 1.3 includes support for model deployment to mobile devices, quantization, and front-end improvements, like the ability to name tensors. We’re also launching tools ...

On Oct 15, 2019
@weballergy shared
RT @OpenAI: We've trained an AI system to solve the Rubik's Cube with a human-like robot hand. This is an unprecedented level of dexterity for a robot, and is hard even for humans to do. The system trains in an imperfect simulation and quickly adapts to reality: https://t.co/O04izt3KvO https://t.co/8lGhU2pPck
Open

Solving Rubik’s Cube with a Robot Hand

We've trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand.

On Oct 11, 2019
@ylecun shared
RT @gradientpub: The war between ML frameworks has raged on since the rebirth of deep learning. Who is winning? @cHHillee's data analysis shows clear trends: PyTorch is winning dramatically among researchers, while Tensorflow still dominates industry. #PyTorch #Tensorflow https://t.co/wgQQZTWcuG
Open

The State of Machine Learning Frameworks in 2019

Since deep learning regained prominence in 2012, many machine learning frameworks have clamored to become the new favorite among researchers and industry practitioners. From the early ...

On Oct 11, 2019
@petewarden shared
RT @thinkmariya: We’ve summarized the key ideas of the research paper “AutoML: the survey of the state-of-the-art” from the Hong Kong Baptist University. Check it out to know, on which tasks AutoML already outperforms human-designed models. #AI #AutoML #ML https://t.co/3Perrkg1zc
Open

What’s State Of The Art In AutoML in 2019?

Following the structure of the original paper, we’ll touch upon the available AutoML techniques, summarize existing approaches to Neural Architecture Search (NAS), provide you with the ...

On Oct 10, 2019
@jeremyphoward shared
RT @ylecun: PyTorch 1.3 is live! Mobile device deployment, model quantization, named tensors, crypto, model interpretability, detectron2... https://t.co/yYQoJqbeUi https://t.co/XbQ08r2c8B
Open

PyTorch 1.3 adds mobile, privacy, quantization, and named tensors

The release of PyTorch 1.3 includes support for model deployment to mobile devices, quantization, and front-end improvements, like the ability to name tensors. We’re also launching tools ...

On Oct 15, 2019
@weballergy shared
RT @OpenAI: We've trained an AI system to solve the Rubik's Cube with a human-like robot hand. This is an unprecedented level of dexterity for a robot, and is hard even for humans to do. The system trains in an imperfect simulation and quickly adapts to reality: https://t.co/O04izt3KvO https://t.co/8lGhU2pPck
Open

Solving Rubik’s Cube with a Robot Hand

We've trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand.

On Oct 11, 2019
@ylecun shared
RT @gradientpub: The war between ML frameworks has raged on since the rebirth of deep learning. Who is winning? @cHHillee's data analysis shows clear trends: PyTorch is winning dramatically among researchers, while Tensorflow still dominates industry. #PyTorch #Tensorflow https://t.co/wgQQZTWcuG
Open

The State of Machine Learning Frameworks in 2019

Since deep learning regained prominence in 2012, many machine learning frameworks have clamored to become the new favorite among researchers and industry practitioners. From the early ...

On Oct 11, 2019
@petewarden shared
RT @thinkmariya: We’ve summarized the key ideas of the research paper “AutoML: the survey of the state-of-the-art” from the Hong Kong Baptist University. Check it out to know, on which tasks AutoML already outperforms human-designed models. #AI #AutoML #ML https://t.co/3Perrkg1zc
Open

What’s State Of The Art In AutoML in 2019?

Following the structure of the original paper, we’ll touch upon the available AutoML techniques, summarize existing approaches to Neural Architecture Search (NAS), provide you with the ...

On Oct 10, 2019
@MSFTResearch shared
"It's a living, breathing thing and it is at the heart of the building." Microsoft's building 99 is now home to Ada, a two-story structure that translates anonymized data into a choreographed dance of color and light: https://t.co/X1SDbL98l0 https://t.co/jv2rLcytry
Open

Smiles beam and walls blush: Architecture meets AI at Microsoft

Ada, a new art installation by Jenny Sabin for Microsoft's Artist in Residence program, is a fusion of art, architecture and AI.

On Oct 10, 2019
@pabbeel shared
Much looking forward to catching up with friends and colleagues, and making new ones at @CMU_Robotics tomorrow! Seminar at 3pm in 1305 Newell Simon Hall. https://t.co/lVgKUhWmjY
Open

Deep Learning for Robotics

Abstract: Programming robots remains notoriously difficult.  Equipping robots with the ability to learn would by-pass the need for what otherwise often ends up being time-consuming task ...

On Oct 15, 2019
@shakir_za shared
RT @vukosi: Go Tsamaya Ke Go Bona: Deep Learning Indaba #3 - A journey just beginning https://t.co/NjOw5iK95v @DeepIndaba #sautiyetu #DLIndaba2019 #Masakhane https://t.co/UnMrhmT97y
Open

Go Tsamaya Ke Go Bona: Deep Learning #3 - A journey just beginning

What is the Deep Learning Indaba?, University of Pretoria

On Oct 15, 2019
@MSFTResearch shared
“We had a strange theorem that was very, very simple, and somehow, we were smart enough to give it a catchy name.” Guest speaker Léon Bottou of @Facebook talks “convexity à la carte” and what it says about approximation properties and global minimization: https://t.co/3rDGg7VdES
Open

AI Institute “Geometry of Deep Learning” 2019 [Day 1 | Session 3]

Deep learning is transforming the field of artificial intelligence, yet it is lacking solid theoretical underpinnings. This state of affair significantly hinders further progress, as ...

On Oct 10, 2019
@peteskomoroch shared
Latest issue of the Projects To Know newsletter #8 from @sarahcat21 @AmplifyPartners: Task-Relevant Adversarial Imitation Learning, Topical-Chat, FaceForensics++ https://t.co/xpybPBthSY
Open

View this email in your browser

Devoted to machine learning and data science, Projects to Know is an essential weekly newsletter for anyone who wants keeps tabs on the latest research, open source projects and industry ...