should we create official chat for the channel to discuss links, answer common question and to flood (during nighttime)?
Anonymous Poll
25%
1. yes( I will actively participate in the discussion )
39%
2. yes(I will join and silently read)
16%
3.yes( I will join and mute the chat,ocassionally reading conversations)
15%
4. I will not join
5%
5.yes ( I will join and volunteer to keep the chat and discussions clean and productive)
The Best Machine Learning Research of 2019 So Far - ODSC - Open Data Science - Medium
https://medium.com/@ODSC/the-best-machine-learning-research-of-2019-so-far-954120947794
https://t.iss.one/ArtificialIntelligenceArticles
https://medium.com/@ODSC/the-best-machine-learning-research-of-2019-so-far-954120947794
https://t.iss.one/ArtificialIntelligenceArticles
Medium
The Best Machine Learning Research of 2019 So Far
The uses of machine learning are expanding rapidly. Already in 2019, significant research has been done in exploring new vistas for the use…
Elon Musk Might Be Right. New Research Exposes Vulnerabilities In LiDAR-based Autonomous Vehicles
https://www.analyticsindiamag.com/lidar-adversarial-objects-research-vulnerabilities-drawbacks/
paper Adversarial Objects Against LiDAR-Based AutonomousDriving Systems https://arxiv.org/pdf/1907.05418v1.pdf
https://www.analyticsindiamag.com/lidar-adversarial-objects-research-vulnerabilities-drawbacks/
paper Adversarial Objects Against LiDAR-Based AutonomousDriving Systems https://arxiv.org/pdf/1907.05418v1.pdf
Analytics India Magazine
Elon Musk Might Be Right. New Research Exposes Vulnerabilities In LiDAR-based Autonomous Vehicles
The authors propose an optimization-based approach LiDAR-Adv that can escape the LiDAR-based detection systems under various conditions.
Learning and Reasoning with Graph-Structured Representations
ICML 2019 Workshop
https://graphreason.github.io/schedule.html
ICML 2019 Workshop
https://graphreason.github.io/schedule.html
MintNet: Building Invertible Neural Networks with Masked Convolutions
Song et al.: https://arxiv.org/abs/1907.07945
#machinelearning #neuralnetworks #neuralnetwork
Song et al.: https://arxiv.org/abs/1907.07945
#machinelearning #neuralnetworks #neuralnetwork
arXiv.org
MintNet: Building Invertible Neural Networks with Masked Convolutions
We propose a new way of constructing invertible neural networks by combining simple building blocks with a novel set of composition rules. This leads to a rich set of invertible architectures,...
Efficient Video Generation on Complex Datasets
Paper: https://arxiv.org/abs/1907.06571
They used chainer implementation for t-gan : https://github.com/pfnet-research/tgan
DeepMind did it again - they created realistic videos by just watching a ton of youtube videos.
Paper: https://arxiv.org/abs/1907.06571
They used chainer implementation for t-gan : https://github.com/pfnet-research/tgan
DeepMind did it again - they created realistic videos by just watching a ton of youtube videos.
arXiv.org
Adversarial Video Generation on Complex Datasets
Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale. We attempt to carry this success to the field of video modeling by showing that...
Probing Neural Network Comprehension of Natural Language Arguments
"We are surprised to find that BERT's peak performance of 77% on the Argument Reasoning Comprehension Task reaches just three points below the average untrained human baseline. However, we show that this result is entirely accounted for by exploitation of spurious statistical cues in the dataset. We analyze the nature of these cues and demonstrate that a range of models all exploit them."
Timothy Niven and Hung-Yu Kao: https://arxiv.org/abs/1907.07355
#naturallanguage #neuralnetwork #reasoning #unsupervisedlearning
"We are surprised to find that BERT's peak performance of 77% on the Argument Reasoning Comprehension Task reaches just three points below the average untrained human baseline. However, we show that this result is entirely accounted for by exploitation of spurious statistical cues in the dataset. We analyze the nature of these cues and demonstrate that a range of models all exploit them."
Timothy Niven and Hung-Yu Kao: https://arxiv.org/abs/1907.07355
#naturallanguage #neuralnetwork #reasoning #unsupervisedlearning
PhD fellow in Theoretical Machine Learning
University of Copenhagen, Denmark
More Details: https://www.marktechpost.com/job/phd-fellow-in-theoretical-machine-learning/
Department of Computer Science, Faculty of Science at University of Copenhagen is offering a PhD scholarship in Theoretical Machine Learning commencing 01.10.2019 or as soon as possible thereafter.
University of Copenhagen, Denmark
More Details: https://www.marktechpost.com/job/phd-fellow-in-theoretical-machine-learning/
Department of Computer Science, Faculty of Science at University of Copenhagen is offering a PhD scholarship in Theoretical Machine Learning commencing 01.10.2019 or as soon as possible thereafter.
MarkTechPost
PhD fellow in Theoretical Machine Learning | MarkTechPost
Department of Computer Science, Faculty of Science at University of Copenhagen is offering a PhD scholarship in Theoretical Machine Learning commencing 01.10.2019 or as soon as possible thereafter. Description of the scientific environment The student will…
Deep Learning and Medical Imaging: Part 2 🎯]
If you're a crafty AI engineer who wants to play with code to learn how things work, just keep reading !
In this post, you'll learn how to use PyTorch to train an Anterior Ligament Cruciate tear classifier that successfully detects these injuries from the MRNet MRI dataset with a very high performance (AUC > 0.95)
You'll dive into the code and go through various tips and tricks ranging from transfer learning to data augmentation, stacking and handling medical images.
You'll also learn about optimization tricks as well as how to organize code efficiently with neural architecture design.
Link to part 2: https://ahmedbesbes.com/automate-the-diagnosis-of-knee-injuries-with-deep-learning-part-2-building-an-acl-tear-classifier.html
Github repo with full code: https://github.com/ahmedbesbes/mrnet
#deeplearning #mediclaimaging #computervision
If you're a crafty AI engineer who wants to play with code to learn how things work, just keep reading !
In this post, you'll learn how to use PyTorch to train an Anterior Ligament Cruciate tear classifier that successfully detects these injuries from the MRNet MRI dataset with a very high performance (AUC > 0.95)
You'll dive into the code and go through various tips and tricks ranging from transfer learning to data augmentation, stacking and handling medical images.
You'll also learn about optimization tricks as well as how to organize code efficiently with neural architecture design.
Link to part 2: https://ahmedbesbes.com/automate-the-diagnosis-of-knee-injuries-with-deep-learning-part-2-building-an-acl-tear-classifier.html
Github repo with full code: https://github.com/ahmedbesbes/mrnet
#deeplearning #mediclaimaging #computervision
Ahmed BESBES - Data Science Portfolio
Automate the diagnosis of Knee Injuries with Deep Learning part 2: Building an ACL tear classifier
In this post, you'll build up on the intuitions you gathered on MRNet data by following the previous post. You'll learn how to use PyTorch to train an ACL tear classifier that sucessfully detects these injuries from MRIs with a very high performance. We'll…
Can Unconditional Language Models Recover Arbitrary Sentences?
Subramani et al.: https://arxiv.org/abs/1907.04944
#ArtificialIntelligence #LanguageModels #MachineLearning
Subramani et al.: https://arxiv.org/abs/1907.04944
#ArtificialIntelligence #LanguageModels #MachineLearning
Natural Adversarial Examples
Hendrycks et al.: https://arxiv.org/abs/1907.07174) arxiv.org/abs/1907.07174
Dataset and code: https://github.com/hendrycks/natural-adv-examples
#MachineLearning #ComputerVision #PatternRecognition
Hendrycks et al.: https://arxiv.org/abs/1907.07174) arxiv.org/abs/1907.07174
Dataset and code: https://github.com/hendrycks/natural-adv-examples
#MachineLearning #ComputerVision #PatternRecognition
arXiv.org
Natural Adversarial Examples
We introduce two challenging datasets that reliably cause machine learning model performance to substantially degrade. The datasets are collected with a simple adversarial filtration technique to...
Job Opening for Machine Learning Engineer in Bangladesh!!
Vacancy: 4 or more.
Salary: 40,000 BDT to 80,000 BDT
Employment Status: Full time.
Job Location: Dhaka Division, Bangladesh
(Joining date for selected candidates will be around November, 2019)
Job position: Machine Learning Engineer
Job Responsibilities:
1. Directing clients to a solution with Machine learning
2. Research on state of the art architecture or new model
3. Data analysis and visualization
Educational Requirements:
○ Bachelor of Science (BSc) in Computer Science or Applied Mathematics.
○ (Master’s/PhD with research experience in machine learning field is highly appreciable.)
Skill & Experience Requirements:
○ Practical knowledge of AI techniques such as machine learning, deep learning, optimization algorithms.
○ Experience of using machine learning framework such as TensorFlow, Keras, PyTorch, Chainer, etc.
○ Fluency in Python, R or C ++.
○ Sound knowledge of Linear Algebra, basic of Statistics, Data Structure, basic Computer Science Algorithms.
○ Basic Computer Science knowledge, e.g. operating system, computer architecture, networking, etc.
○ Software development experience in projects and teams.
○ Development experience using version control system by Git et al., AWS or GCP, Docker.
Compensation and Other Benefits
○ Performance bonus
○ Weekly 2 holidays
○ Festival Bonus: 2
○ Lunch Facilities
○ Salary Review: Yearly
Application Deadline: 21 July, 2019
How to apply:
Please find further details and apply from the following link: https://www.chowagiken.co.jp/job/
Note: Chowa Giken Company Seminar will be held in 19th July, 2019
from 11:00-12:00 BDT (1H) at BJIT LTD 6 floor seminar room.
If you are interested to apply for our position, we would be appreciated your participation
Vacancy: 4 or more.
Salary: 40,000 BDT to 80,000 BDT
Employment Status: Full time.
Job Location: Dhaka Division, Bangladesh
(Joining date for selected candidates will be around November, 2019)
Job position: Machine Learning Engineer
Job Responsibilities:
1. Directing clients to a solution with Machine learning
2. Research on state of the art architecture or new model
3. Data analysis and visualization
Educational Requirements:
○ Bachelor of Science (BSc) in Computer Science or Applied Mathematics.
○ (Master’s/PhD with research experience in machine learning field is highly appreciable.)
Skill & Experience Requirements:
○ Practical knowledge of AI techniques such as machine learning, deep learning, optimization algorithms.
○ Experience of using machine learning framework such as TensorFlow, Keras, PyTorch, Chainer, etc.
○ Fluency in Python, R or C ++.
○ Sound knowledge of Linear Algebra, basic of Statistics, Data Structure, basic Computer Science Algorithms.
○ Basic Computer Science knowledge, e.g. operating system, computer architecture, networking, etc.
○ Software development experience in projects and teams.
○ Development experience using version control system by Git et al., AWS or GCP, Docker.
Compensation and Other Benefits
○ Performance bonus
○ Weekly 2 holidays
○ Festival Bonus: 2
○ Lunch Facilities
○ Salary Review: Yearly
Application Deadline: 21 July, 2019
How to apply:
Please find further details and apply from the following link: https://www.chowagiken.co.jp/job/
Note: Chowa Giken Company Seminar will be held in 19th July, 2019
from 11:00-12:00 BDT (1H) at BJIT LTD 6 floor seminar room.
If you are interested to apply for our position, we would be appreciated your participation
NIPS 2017 Invited talk
"Deep Reinforcement Learning with Subgoals"
By David Silver: https://vimeo.com/249557775
#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks #ReinforcementLearning
"Deep Reinforcement Learning with Subgoals"
By David Silver: https://vimeo.com/249557775
#ArtificialIntelligence #DeepLearning #MachineLearning #NeuralNetworks #ReinforcementLearning
Vimeo
Invited talk:Deep Reinforcement Learning with Subgoals(David Silver)
If you're curious how hair recoloring worked on FaceApp, this might give you a hint! (CVPR 2019)
https://www.profillic.com/paper/arxiv:1907.06740
https://www.profillic.com/paper/arxiv:1907.06740
Profillic
Profillic: AI research & source code to supercharge your projects
Explore state-of-the-art in machine learning, AI, and robotics research. Browse papers, source code, models, and more by topics and authors. Connect with researchers and engineers working on related problems in machine learning, deep learning, natural language…
Find The Most Updated and Free Artificial Intelligence, Machine Learning, Data Science, Deep Learning, Mathematics, Python, R Programming Resources.
Full List: https://www.marktechpost.com/free-resources/
📷CS109 Data Science- Harvard
📷Data Science Essentials- Microsoft
📷Learning from Data – California Institute of Technology
📷The Mathematics of Machine Learning by UC Berkeley
📷"Foundations of Data Science" Book by Avrim Blum, John Hopcroft, and Ravindran Kannan
📷Python Data Science Handbook by Jake VanderPlas
Full List: https://www.marktechpost.com/free-resources/
📷CS109 Data Science- Harvard
📷Data Science Essentials- Microsoft
📷Learning from Data – California Institute of Technology
📷The Mathematics of Machine Learning by UC Berkeley
📷"Foundations of Data Science" Book by Avrim Blum, John Hopcroft, and Ravindran Kannan
📷Python Data Science Handbook by Jake VanderPlas
Best Paper Awards in Computer Science (since 1996)
Conferences: AAAI ACL CHI CIKM CVPR FOCS FSE ICCV ICML ICSE IJCAI INFOCOM KDD MOBICOM NSDI OSDI PLDI PODS S&P SIGCOMM SIGIR SIGMETRICS SIGMOD SODA SOSP STOC UIST VLDB WWW
By Jeff Huang : https://jeffhuang.com/best_paper_awards.html
#artificialintelligence #computerscience #machinelearning
Conferences: AAAI ACL CHI CIKM CVPR FOCS FSE ICCV ICML ICSE IJCAI INFOCOM KDD MOBICOM NSDI OSDI PLDI PODS S&P SIGCOMM SIGIR SIGMETRICS SIGMOD SODA SOSP STOC UIST VLDB WWW
By Jeff Huang : https://jeffhuang.com/best_paper_awards.html
#artificialintelligence #computerscience #machinelearning
Deep Learning to Assess Long-term Mortality From Chest Radiographs
https://jamanetwork.com/journals/jamanetworkopen/article-abstract/2738349
https://jamanetwork.com/journals/jamanetworkopen/article-abstract/2738349
Generative Deep Learning book
https://shop.oreilly.com/product/0636920189817.do
https://shop.oreilly.com/product/0636920189817.do