🔻10 Best Machine Learning Frameworks in 2020

1. #TensorFlow
2. Google Cloud ML Learning
3. Apache Mahout
4. Shogun
5. Sci-Kit Learn
6. #PyTorch or TORCH
7. H2O
8. Microsoft Cognitive Toolkit (#CNTK)
9. #Apache MXNet
10. Apple's Core ML

—————————————————
https://www.cubix.co/blog/best-machine-learning-frameworks-in-2020

📌Via: @cedeeplearning

#deeplearning
#machinelearning
#datascience

🔻Data Scientist Positions Available at Princeton

Princeton University is building a community of data scientists to work in partnership with its world-renowned faculty and students to help solve data-driven research problems. You will work with faculty in a collaborative, multidisciplinary environment and actively contribute your skills to advance scientific discovery and have access to Princeton's first-class resources, the opportunity to co-author academic publications, to offer short courses and workshops on data science, and to collaborate the larger computational data science community.

———————————————
link: https://csml.princeton.edu/news/data-scientist-positions-available-princeton

📌Via: @cedeeplearning

#datascience
#machinelearning
#deeplearning
#university
#community

🔹How Algorithms Can Predict Our Intentions Faster Than We Can

Artificial Intelligence (AI) and Natural Language Processing (NLP) can gather data from anywhere online where we leave a mark. This includes our social media posts, our email, and even any small comments we leave on blog posts. Every trace we leave online allows NLP to track and predict our future decisions.
This article highlight how NLP can impact our day-to-day lives with the use of case studies.

——————————————————
https://www.entrepreneur.com/article/328776

📌Via: @cedeeplearning

#NLP
#AI
#machinelearning
#deeplearning
#algorithm

https://www.paperswithcode.com/

🔹Look at these amazing websites for machine learning and deep learning projects along with the research papers and corresponding codes. It's a good resource for inviting yourself into challenge.

📌Via: @cedeeplearning

🔻Basic-Mathematics-for-Machine-Learning

GitHub is home to over 40 million developers working together to host and review code, manage projects, and build software together.

——————————————
📌Via: @cedeeplearning

https://github.com/hrnbot/Basic-Mathematics-for-Machine-Learning/blob/master/Cheat%20Sheet%20Suggested%20by%20Siraj%20Raval/Calculus%20Cheat%20Sheet.pdf

#machinelearning
#deeplearning
#neuralnetworks

🔹Microsoft Rolls Out 🔻Free🔻 AI Courses Geared Toward Business Leaders

Microsoft is releasing a new set of artificial intelligence courses geared toward business leaders. The free instructional videos and case studies focus on the less technical aspects of the technology as it applies to top execs attempting to integrate AI, including strategy, company culture and ethical responsibilities, into their operations.

————————————————
📌Via: @cedeeplearning

https://www.adweek.com/digital/microsoft-rolls-out-free-ai-courses-geared-toward-business-leaders/amp/

#machinelearning
#deeplearning
#AI
#free

🟢 74 Summaries of Machine Learning and NLP Research

📗 you will find short summaries of a number of different research papers published in the areas of Machine Learning and Natural Language Processing in the past couple of years (2017-2019). They cover a wide range of different topics, authors and venues.

🔗http://www.marekrei.com/blog/74-summaries-of-machine-learning-and-nlp-research/

Via: @cedeeplearning 📌

📗 Adapted Center and Scale Prediction: More Stable and More Accurate

📕 In order to enjoy the simplicity of anchor-free detectors and the accuracy of two-stage ones simultaneously, they have proposed some adaptations based on a detector, Center and Scale Prediction(CSP). The main contributions of their paper are:

1. Improve the robustness of CSP and make it easier to train.
2. Propose a novel method to predict width, namely compressing width.
3. Achieve the second best performance on CityPersons benchmark, i.e. 9.3% log-average miss rate(MR) on reasonable set, 8.7% MR on partial set and 5.6% MR on bare set, which shows an anchor-free and one-stage detector can still have high accuracy.
4. Explore some capabilities of Switchable Normalization which are not mentioned in its original paper.

Link: http://arxiv.org/abs/2002.09053

Via: @cedeeplearning 📌
🟢 Other social media: https://linktr.ee/cedeeplearning

Neural network architectures

Deep neural networks and Deep Learning are powerful and popular algorithms. And a lot of their success lays in the careful design of the neural network architecture.

https://towardsdatascience.com/neural-network-architectures-156e5bad51ba

Via: @cedeeplearning
Other social media: https://linktr.ee/cedeeplearning

📗Progressive Learning and Disentanglement of Hierarchical Representations

📕present a strategy to progressively learn independent hierarchical representations from high- to low-levels of abstractions. The model starts with learning the most abstract representation, and then progressively grow the network architecture to introduce new representations at different levels of abstraction.
arXiv, Apr 3, 2020
Link: http://arxiv.org/abs/2002.10549


Via: @cedeeplearning📌
🟢Other social media: https://linktr.ee/cedeeplearning

Machine Learning Mind Map

📗 This is an interactive chart. Click on the icons to go to a specific sub-field/section.
Straightforward A-Z explanation of ML algorithms with Python implementation and clearly explained math behind -
Link: thelearningmachine.ai/ml

Via: @cedeeplarning📌
🟢 Other social media: https://linktr.ee/cedeeplearning

🔹MIT Deep Learning Basics: Introduction and Overview with TensorFlow

As part of the MIT Deep Learning series of lectures and GitHub tutorials, we are covering the basics of using neural networks to solve problems in computer vision, natural language processing, games, autonomous driving, robotics, and beyond.

📌Via: @cedeeplearning

https://medium.com/tensorflow/mit-deep-learning-basics-introduction-and-overview-with-tensorflow-355bcd26baf0

#deeplearning
#neuralnetworks
#TensorFlow
#machinelearning

🔹Olympics Win Gold Medal For Big Data

Nearly 60 GB of information per second is expected to travel across British Telecom’s networks during the Olympic Games. Unsurprisingly social media has generated reams of content during the games. The estimated 845 million monthly active Facebook users are expected to be responsible for more than 15 terabytes of data each day, while Twitter is expecting over 13,000 tweets per second.

link: https://www.forbes.com/sites/netapp/2012/08/08/olympic-charter-big-data-airplane/#17ce8a38180f

📌Via: @cedeeplearning

📌Other Social Media: https://linktr.ee/cedeeplearning
#bigdata
#machinelearning
#datascience

🔻Some points to visualizing your data

📌Via: @cedeeplearning
📌Other social media: https://linktr.ee/cedeeplearning

link: https://policyviz.com/2018/08/07/dataviz-cheatsheet/

#visualization
#bigdata
#machinelearning
#datascience

🔻The 8 Data Science Skills

1. Programming Skills
2. Statistics
3. Machine Learning
4. Multivariable Calculus & Linear Algebra
5. Data Wrangling
6. Data Visualization & Communication
7. Software Engineering
8. Data Intuition

📌Via: @cedeeplearning
📌Other social media: https://linktr.ee/cedeeplearning

link: https://blog.udacity.com/2014/11/data-science-job-skills.html

#datascience
#bigdata
#skill
#machineleraning

📗StyleGAN2 Distillation for Feed-forward Image Manipulation

🎉A new way to distill a particular image manipulation of StyleGAN2 into image-to-image network trained in paired way. The resulting pipeline is an alternative to existing GANs, trained on unpaired data. They provide results of human faces' transformation: gender swap, aging/rejuvenation, style transfer and image morphing. The quality of generation using this method is comparable to StyleGAN2 backpropagation and current state-of-the-art methods in these particular tasks.
By Yandex.MILAB 🎉 2020

📝 arxiv.org/abs/2003.03581

Via: @CEdeeplearning 📌
🟢 Other social media handles: https://linktr.ee/cedeeplearning

🔹Deep Learning vs. Machine Learning Models

One topic we find very interesting and will freely admit consumes much of our free time is machine learning. We devote considerable time to researching meaningful business-level topics related to AI, deep learning and machine learning.

If you’re unsure of the core differences between the two, this brief video by MATLAB gives an excellent quick and digestible overview.

——————————————————
📌Via: @cedeeplearning
📌Other social media: https://linktr.ee/cedeeplearning

🔻link: https://youtu.be/-SgkLEuhfbg

#machinelearning
#deeplearning
#matlab

🔹Achieving Digital Economies of Scale Via Machine Learning and Model Sequencing

As you deploy something as complex as machine learning, you’ll often start the initial work of scoping initiative X, exploring data, surfacing various levels of insights or predictions and deploying the solution into the wild.
The types of “work” we’re talking about here could fall in the range of any of the following:

1. A specific set of data exploration protocols
2. An outlier that was discovered and that may apply to subsequent models
3. Specific features engineered for a given reason
4. A given team that properly and adequately ideates
5. Scopes and plans of a given initiative or model
6. Specific meta-data and semantic rules or data points that are cultivated and subsequently documented and disseminated across the proper channels and teams throughout an organization

—————————————
📌Via: @cedeeplearning
📌Other social media: https://linktr.ee/cedeeplearning

Credit: https://www.rocketsource.co/blog/machine-learning-model

🔹The Span of Influence in Machine Learning Models

Each player here is an expert in his own right, he must know what the other influencers in the machine learning model need to succeed. You’ve likely heard us talk about the importance of V-Shaped Teams in the past when discussing the concept of skilling up your team members in areas outside of their immediate expertise. The same concept applies here. Peripheral skills matter a lot because your team cannot successfully build and leverage machine learning models if they’re working in silos.

——————————————
📌Via: @cedeeplearning
📌Other social media: https://linktr.ee/cedeeplearning

Link: https://www.rocketsource.co/blog/machine-learning-models/

#machinelearning
#deeplearning
#datascience

📗 Automating Botnet Detection with Graph Neural Networks

🟢 Botnets are a major source for many network attacks, such as DDoS attacks and spam

(Submitted on 13 Mar 2020)
https://arxiv.org/abs/2003.06344?utm_content=buffer8e745&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer

Via: @cedeeplearning
Other social media: https://linktr.ee/cedeeplearning