To Retrain, or Not to Retrain? Let’s Get Analytical About ML Model Updates
In this ML 101 article, you’ll find answers to questions like, «How often should I retrain a model?», «Should I retrain the model now?», and «Should I retrain, or should I update the model?». Dig in for an easy but important piece to read!
https://bit.ly/3qVwDRL
In this ML 101 article, you’ll find answers to questions like, «How often should I retrain a model?», «Should I retrain the model now?», and «Should I retrain, or should I update the model?». Dig in for an easy but important piece to read!
https://bit.ly/3qVwDRL
Evidentlyai
To retrain, or not to retrain? Let’s get analytical about ML model updates.
Is it time to retrain your machine learning model? Even though data science is all about… data, the answer to this question is surprisingly often based on a gut feeling. Can we do better?
PlanSys2: A Planning System Framework for ROS2
In this paper, the researchers reveal the ROS2 Planning System (PlanSys2), a framework for symbolic planning that incorporates novel approaches for execution on robots working in demanding environments. PlanSys2 aims to be the reference task planning framework in ROS2, the latest version of the {\em de facto} standard in robotics software development.
Paper — https://bit.ly/3qRr8U4
Code
— https://bit.ly/3yy3Sx5
In this paper, the researchers reveal the ROS2 Planning System (PlanSys2), a framework for symbolic planning that incorporates novel approaches for execution on robots working in demanding environments. PlanSys2 aims to be the reference task planning framework in ROS2, the latest version of the {\em de facto} standard in robotics software development.
Paper — https://bit.ly/3qRr8U4
Code
— https://bit.ly/3yy3Sx5
A Discourse on Reinforcement Learning [Part 1]
This is the first of the 3-article series «A Discourse on Reinforcement Learning» that kicks off with a holistic overview of Reinforcement Learning with an expansive setting. Save the article not to miss parts 2 and 3 about more advanced RL topics.
https://bit.ly/3ApUZr0
This is the first of the 3-article series «A Discourse on Reinforcement Learning» that kicks off with a holistic overview of Reinforcement Learning with an expansive setting. Save the article not to miss parts 2 and 3 about more advanced RL topics.
https://bit.ly/3ApUZr0
Medium
A Discourse on Reinforcement Learning
Part I — AN EXPANSIVE SETTING
The MultiBERTs: BERT Reproductions for Robustness Analysis
In this paper, the international team of researchers introduce MultiBERTs: a set of 25 BERT-base checkpoints, trained with similar hyper-parameters as the original BERT model but differing in random initialization and data shuffling. The aim is to enable researchers to draw robust and statistically justified conclusions about pre-training procedures.
Paper — https://bit.ly/3ylSVyh
Code — https://bit.ly/3dGW3wY
In this paper, the international team of researchers introduce MultiBERTs: a set of 25 BERT-base checkpoints, trained with similar hyper-parameters as the original BERT model but differing in random initialization and data shuffling. The aim is to enable researchers to draw robust and statistically justified conclusions about pre-training procedures.
Paper — https://bit.ly/3ylSVyh
Code — https://bit.ly/3dGW3wY
An Introduction to Object Detection with Deep Learning
In this article, you’ll learn the basics of using object-detection deep learning networks. It features a review of CNNs, object detection datasets, R-CNN models, and YOLO. If you’re looking for a review of deep learning architectures for object detection, this one’s for you.
https://bit.ly/3yppLOY
In this article, you’ll learn the basics of using object-detection deep learning networks. It features a review of CNNs, object detection datasets, R-CNN models, and YOLO. If you’re looking for a review of deep learning architectures for object detection, this one’s for you.
https://bit.ly/3yppLOY
TechTalks
An introduction to object detection with deep learning
Learn how deep neural networks detect objects in images in this primer on object detection with deep learning.
AutoFormer: Searching Transformers for Visual Recognition
AutoFormer is a new one-shot architecture search framework for vision transformer search. It entangles the weights of different blocks in the same layers during supernet training. The trained supernet allows thousands of subnets to be well-trained. Their performance with weights inherited from the supernet is comparable to those retrained from scratch.
Paper — https://bit.ly/3dKRiCl
Code — https://bit.ly/3As6zln
AutoFormer is a new one-shot architecture search framework for vision transformer search. It entangles the weights of different blocks in the same layers during supernet training. The trained supernet allows thousands of subnets to be well-trained. Their performance with weights inherited from the supernet is comparable to those retrained from scratch.
Paper — https://bit.ly/3dKRiCl
Code — https://bit.ly/3As6zln
Vectorization Techniques in NLP [Guide]
This comprehensive guide by the Neptune team will help you dig deep into Natural Language Processing and explore all the main branches of word embeddings, starting from naive count-based methods to sub-word level contextual embeddings.
https://bit.ly/3hBiODH
This comprehensive guide by the Neptune team will help you dig deep into Natural Language Processing and explore all the main branches of word embeddings, starting from naive count-based methods to sub-word level contextual embeddings.
https://bit.ly/3hBiODH
neptune.ai
Vectorization Techniques in NLP [Guide] - neptune.ai
Natural Language is how we, humans, exchange ideas and opinions. There are two main mediums for natural language – speech and text. Listening and reading are effortless for a healthy human, but they’re difficult for a machine learning algorithm. That’s why…
DivergentNets: Medical Image Segmentation by Network Ensemble
In this paper, the team of researchers explore new methods of detection of colon polyps with machine learning. They propose DivergentNets, an ensemble of such well-known segmentation models as UNet++, FPN, DeepLabv3, and DeepLabv3+, to produce more generalizable medical image segmentation masks.
Paper — https://bit.ly/3jMNG6M
Code — https://bit.ly/3xqB21i
In this paper, the team of researchers explore new methods of detection of colon polyps with machine learning. They propose DivergentNets, an ensemble of such well-known segmentation models as UNet++, FPN, DeepLabv3, and DeepLabv3+, to produce more generalizable medical image segmentation masks.
Paper — https://bit.ly/3jMNG6M
Code — https://bit.ly/3xqB21i
Continuously Improving Recommender Systems for Competitive Advantage Using NVIDIA Merlin and MLOps
In this article, you’ll explore how to use NVIDIA Merlin, an application framework that accelerates all phases of recommender system development on NVIDIA GPUs, to implement a complete MLOps pipeline.
https://bit.ly/2Uonwwy
In this article, you’ll explore how to use NVIDIA Merlin, an application framework that accelerates all phases of recommender system development on NVIDIA GPUs, to implement a complete MLOps pipeline.
https://bit.ly/2Uonwwy
NVIDIA Developer Blog
Continuously Improving Recommender Systems for Competitive Advantage Using NVIDIA Merlin and MLOps | NVIDIA Developer Blog
This posts shares how NVIDIA Merlin components fit into a complete MLOps pipeline to operationalize a recommendation system, and continuously deliver improvements in production.
Are you subscribed to our weekly newsletter yet? What are you waiting for, then? Fill in your email and get instant access to all the AI/ML goodies in one go. Looking forward to having you as one of our amazing subscribers!
https://dataphoenix.info/tag/digest/
https://dataphoenix.info/tag/digest/
Last week, we rebranded and restarted our digest. What does it mean, exactly?
For you, it means that you’re going to get updated about all things happening in the AI world on a new level. We’re hyped and ready to give you more and be there for you when you need guidance. Our weekly newsletter will be sent out as usual every Thursday (so no worries), but we’d also love to coop more with the community. We’ve planned tons of new activities for you, so make sure that you follow us on social media — and be ready to get energized!
https://bit.ly/2VjWN4O
For you, it means that you’re going to get updated about all things happening in the AI world on a new level. We’re hyped and ready to give you more and be there for you when you need guidance. Our weekly newsletter will be sent out as usual every Thursday (so no worries), but we’d also love to coop more with the community. We’ve planned tons of new activities for you, so make sure that you follow us on social media — and be ready to get energized!
https://bit.ly/2VjWN4O
As a beginner, the first who you should know about is Geoffrey Hinton. He's a computer scientist and his biggest achievement is work on artificial neural networks. Hinton is famous as one of the most important figures in the deep learning community. Hinton was elected a Fellow of the Royal Society (FRS) in 1998. Additionally he was the first winner of the Rumelhart Prize in 2001. The fame of the AlexNet came when he in collaboration with his students Alex Krizhevsky and Ilya Sutskever designed for the ImageNet challenge 2012. This event was a breakthrough in the field of computer vision.
Geoffrey Hinton was one of the researchers who introduced the backpropagation algorithm and the first to use backpropagation for learning word embeddings. His other contributions to neural network research include Boltzmann machines, distributed representations, time-delay neural nets, mixtures of experts, variational learning and deep learning. His research group in Toronto made major breakthroughs in deep learning that revolutionized speech recognition and object classification.
https://bit.ly/3AKwl4r
Geoffrey Hinton was one of the researchers who introduced the backpropagation algorithm and the first to use backpropagation for learning word embeddings. His other contributions to neural network research include Boltzmann machines, distributed representations, time-delay neural nets, mixtures of experts, variational learning and deep learning. His research group in Toronto made major breakthroughs in deep learning that revolutionized speech recognition and object classification.
https://bit.ly/3AKwl4r
Are you tired of lockdowns? We for sure are!
We at Data Phoenix, together with Autodoc and VITech, are excited to invite you to an offline meetup of Odesa’s Open Data Science community that’s going to take place June 14, 6:30 PM — 9 PM. We’ll cover such topics as data management, object detection, and more. Most importantly, though, we’re going to network for real — that’s what we’ve been missing all these long quarantine months, right?
Because the number of seats is limited, we’re going to have an online session as well. The talks will be in Russian.
The event is free, but registration is required. So kindly register right away!👇🏻
https://bit.ly/3hVZCkb
#meetup #DataScience #DataManagement #ObjectDetection
We at Data Phoenix, together with Autodoc and VITech, are excited to invite you to an offline meetup of Odesa’s Open Data Science community that’s going to take place June 14, 6:30 PM — 9 PM. We’ll cover such topics as data management, object detection, and more. Most importantly, though, we’re going to network for real — that’s what we’ve been missing all these long quarantine months, right?
Because the number of seats is limited, we’re going to have an online session as well. The talks will be in Russian.
The event is free, but registration is required. So kindly register right away!👇🏻
https://bit.ly/3hVZCkb
#meetup #DataScience #DataManagement #ObjectDetection
To get a better idea about how the industry works, sometimes it makes sense to watch a movie, just to get inspired by the power of talent and knowledge. Our team has prepared a few movies like that to demonstrate how machine learning can be depicted in a work of art.
Blade Runner 2049
One of the most impactful and in-depth storylines about smart machines. Blade Runner 2049 is a movie made for today’s machine learning age. In it, the replicants are “strong AI” — artificial general intelligence (AGI) that enables a machine to carry out any human task and even undertake advanced decisions on its own. Strong AI means replicants are stronger than humans in every respect and can even experience real emotions. However, the movie also deals with questions of soulless robots having consciousness and whether AI-powered intelligence means real consciousness.
https://bit.ly/36qO03d
Comment your favorite AI movie!👇🏻
Blade Runner 2049
One of the most impactful and in-depth storylines about smart machines. Blade Runner 2049 is a movie made for today’s machine learning age. In it, the replicants are “strong AI” — artificial general intelligence (AGI) that enables a machine to carry out any human task and even undertake advanced decisions on its own. Strong AI means replicants are stronger than humans in every respect and can even experience real emotions. However, the movie also deals with questions of soulless robots having consciousness and whether AI-powered intelligence means real consciousness.
https://bit.ly/36qO03d
Comment your favorite AI movie!👇🏻
4 steps to get a successful AI project
1. Prioritize engineering over data science
As a rule of thumb, engineers can pick up data science skills faster than data scientists can pick up engineering skills. If you have any doubts about that, just work with any Python engineer with 5+ years of experience and passion for AI, rather than the PhD in data science having their first go at building business applications.
2. Go lean
It’s important to minimize risks early on. Structure your project around specific milestones. Make the team focused on launching «live» solutions (i.e. a pilot) in one to three months. When in production, decide whether further development will be worth it.
3. The algorithm doesn’t matter, data does
The algorithm is the least important part of your AI solution. Just choose an algorithm that works. Endlessly upgrading the algorithm is tempting, but it will probably not give you the results you expect. Focus on cleaning your data instead.
4. Communicate
Once the engineering team starts building, they have to make a lot of choices. The better they know your priorities, the more right decisions they can make.
Was it helpful? Let us know!
https://bit.ly/3r0iNxc
1. Prioritize engineering over data science
As a rule of thumb, engineers can pick up data science skills faster than data scientists can pick up engineering skills. If you have any doubts about that, just work with any Python engineer with 5+ years of experience and passion for AI, rather than the PhD in data science having their first go at building business applications.
2. Go lean
It’s important to minimize risks early on. Structure your project around specific milestones. Make the team focused on launching «live» solutions (i.e. a pilot) in one to three months. When in production, decide whether further development will be worth it.
3. The algorithm doesn’t matter, data does
The algorithm is the least important part of your AI solution. Just choose an algorithm that works. Endlessly upgrading the algorithm is tempting, but it will probably not give you the results you expect. Focus on cleaning your data instead.
4. Communicate
Once the engineering team starts building, they have to make a lot of choices. The better they know your priorities, the more right decisions they can make.
Was it helpful? Let us know!
https://bit.ly/3r0iNxc
Happy Monday everyone! Here’s a quick reminder about our meetup this Wednesday.
We at Data Phoenix, together with Autodoc and VITech, are excited to invite you to an offline meetup of Odesa’s Open Data Science community that’s going to take place July 14, 6:30 PM — 9 PM. We’ll cover such topics as data management, object detection, and more. Most importantly, though, we’re going to network for real — that’s what we’ve been missing all these long quarantine months, right?
Because the number of seats is limited, we’re going to have an online session as well. The talks will be in Russian.
The event is free, but registration is required. So kindly register right away!👇🏻
https://bit.ly/3hy0nRB
We at Data Phoenix, together with Autodoc and VITech, are excited to invite you to an offline meetup of Odesa’s Open Data Science community that’s going to take place July 14, 6:30 PM — 9 PM. We’ll cover such topics as data management, object detection, and more. Most importantly, though, we’re going to network for real — that’s what we’ve been missing all these long quarantine months, right?
Because the number of seats is limited, we’re going to have an online session as well. The talks will be in Russian.
The event is free, but registration is required. So kindly register right away!👇🏻
https://bit.ly/3hy0nRB
Catalyst.Neuro: A 3D Brain Segmentation Pipeline for MRI
In this article, you’ll learn about Catalyst.Neuro, an advanced brain segmentation pipeline, about its fundamental concepts implemented and different deep learning models to perform and complete brain segmentation tasks.
https://bit.ly/3ATuBpO
In this article, you’ll learn about Catalyst.Neuro, an advanced brain segmentation pipeline, about its fundamental concepts implemented and different deep learning models to perform and complete brain segmentation tasks.
https://bit.ly/3ATuBpO
Medium
Catalyst.Neuro: A 3D Brain Segmentation Pipeline for MRI
In this post, we will go through a neuroimaging project Catalyst.Neuro and compare deep learning models on brain segmentation task.
Data Phoenix pinned «Happy Monday everyone! Here’s a quick reminder about our meetup this Wednesday. We at Data Phoenix, together with Autodoc and VITech, are excited to invite you to an offline meetup of Odesa’s Open Data Science community that’s going to take place July 14…»
Effortless Distributed Training of Ultra-Wide GCNs
Graph independent subnetwork training (GIST) is a distributed training framework for large-scale graph convolutional networks (GCNs). It massively accelerates the training of GCNs for any architecture and can be used to enable training of large-scale models.
https://bit.ly/3k8CCRG
Graph independent subnetwork training (GIST) is a distributed training framework for large-scale graph convolutional networks (GCNs). It massively accelerates the training of GCNs for any architecture and can be used to enable training of large-scale models.
https://bit.ly/3k8CCRG
Medium
Effortless Distributed Training of Ultra-Wide GCNs
An overview of GIST, a novel distributed training framework for large-scale GCNs.
TOP-5 tips for successful career in AI
Tip 1: Educational Requirements
According to teach.com, to start in the artificial intelligence field you’ll typically need a bachelor’s degree in IT, computer science, statistics, data science or a related field. For more advanced work, a master’s or PhD in one of these disciplines may be required.
Having strong STEM skills, including competency in statistics and mathematics, could also be beneficial in an AI engineer career.
Tip 2: Boost Up Your Skills
Beyond education requirements, the following are skills that are important for success:
Critical thinking and collaborative skills: A big part of your AI role will involve using data as a problem solving tool. This will require good communication and teamwork skills to effectively report and explain any insights found in data.
Analytical skills: Successful AI engineers are good with numbers. This requires an ability to think analytically, on the one hand, and to successfully communicate your thoughts and ideas to stakeholders, on the other.
Being business savvy: The ability to connect the dots between the practical world of business (use cases) and the specifics of the ML model (and data required in it) can be helpful to any AI engineer.
Tip 3: Learn Programming Languages
An AI professional should also demonstrate programming language proficiency in one or more of these common computer languages: Python, R, Java, C++
Tip 4: Keep Track of Tools and Frameworks
If you are interested in building up your career in artificial intelligence or you are searching for an artificial intelligence job, then you should know which framework or tool will make your code easy to implement.
Tip 5: Develop Your Own AI Project
You can develop a small project, or you can develop an ongoing project on GitHub. By developing an artificial intelligence project, you can check and test your own abilities.
Was it helpful? Let us know👇🏻
Tip 1: Educational Requirements
According to teach.com, to start in the artificial intelligence field you’ll typically need a bachelor’s degree in IT, computer science, statistics, data science or a related field. For more advanced work, a master’s or PhD in one of these disciplines may be required.
Having strong STEM skills, including competency in statistics and mathematics, could also be beneficial in an AI engineer career.
Tip 2: Boost Up Your Skills
Beyond education requirements, the following are skills that are important for success:
Critical thinking and collaborative skills: A big part of your AI role will involve using data as a problem solving tool. This will require good communication and teamwork skills to effectively report and explain any insights found in data.
Analytical skills: Successful AI engineers are good with numbers. This requires an ability to think analytically, on the one hand, and to successfully communicate your thoughts and ideas to stakeholders, on the other.
Being business savvy: The ability to connect the dots between the practical world of business (use cases) and the specifics of the ML model (and data required in it) can be helpful to any AI engineer.
Tip 3: Learn Programming Languages
An AI professional should also demonstrate programming language proficiency in one or more of these common computer languages: Python, R, Java, C++
Tip 4: Keep Track of Tools and Frameworks
If you are interested in building up your career in artificial intelligence or you are searching for an artificial intelligence job, then you should know which framework or tool will make your code easy to implement.
Tip 5: Develop Your Own AI Project
You can develop a small project, or you can develop an ongoing project on GitHub. By developing an artificial intelligence project, you can check and test your own abilities.
Was it helpful? Let us know👇🏻