Best paper award at #CVPR2019 main idea: seeing around the corner at non-line-of-sight (NLOS) objects by using Fermat paths, which is a new theory of how NLOS photons follow specific geometric paths.
http://imaging.cs.cmu.edu/fermat_paths/assets/cvpr2019.pdf

✴️ @AI_Python_EN

Researchers at Facebook, Princeton, and UC Berkeley have developed a method that uses AI to find and propose the most efficient design for neural networks based on how and where they'll run, such as on mobile processors. #CVPR2019
https://ai.facebook.com/blog/platform-aware-ai-to-design-neural-networks/

✴️ @AI_Python_EN

#CVPR2019 stats

✴️ @AI_Python_EN

Released at #CVPR2019, MediaPipe is Google's new framework for media processing pipelines, combining model-based inference via TensorFlow with traditional CV tasks like optical flow, pose tracking, and more. Used in existing projects like Motion Stills.
https://sites.google.com/view/perception-cv4arvr/mediapipe

✴️ @AI_Python_EN

Presenting some work today on how humans and machines perform when doing collaborative visual search at #CVPR2019! A topic of interest for radiologists, surveillance operators and potentially semi-autonomous driving!

✴️ @AI_Python_EN

Check out Scene Representation Networks:
https://youtu.be/6vMEBWD8O20
new continuous 3D-aware scene representation reconstructs appearance and geometry just from posed images, generalizes across scenes for single-shot reconstruction, and naturally handles non-rigid deformation!
https://arxiv.org/abs/1906.01618
#computervision

✴️ @AI_Python_EN

When ImageNet: A large-scale hierarchical image database was published in 2009, it showed how large-scale datasets could transform neural network algorithms. Now, its author & HAI co-director Dr Fei-Fei li has won the #cvpr2019 award for the retrospective most impactful paper. #AI

✴️ @AI_Python_EN

When marketing researchers use the term "analytics," they are usually broadly referring to predictive analytics, or perhaps text mining and other types of analyses they associate with machine learning and AI.

Back in the '90s, though, "advanced analytics" could refer to econometrics and time series analysis, conjoint analysis and choice modeling, new forms of segmentation, and other non-standard types of multivariate analysis.

Whether or not you call them advanced analytics, in reality, the data source does not matter. People working in marketing research, psychology, sociology, political science, economics and many other fields have been conducting quite sophisticated analyses of survey data, for example, for a very long time.

Predictive analytics, text mining, machine learning and AI also have much longer history in MR than many may realize. They just weren't getting the buzz they now do.

Another area of confusion is that many marketing researchers are under the impression that the "bigger" the data, the more sophisticated the analytics.

In fact, the reverse is often true. Moreover, very familiar methods such as linear regression, binary logistic regression, principle components ("factor") analysis and K-means are widely-used in "big data" analytics.

In the business world, sophisticated analytics of any kind historically have faced several challenges. An obvious one is that most business people aren't statisticians or computer scientists and may find it confusing.

Part of this stems from the way they are sold and, by sold, I mean internally as well. I've learned over the years not to sell technique but to sell the concrete benefits of advanced methods to decision makers. I avoid mention of anything technical unless it is absolutely essential, which is rare. Advanced analytics should not be used as sales gimmicks, IMO, especially by people who do not understand them.

A lot of important decisions can be made without any fancy stuff.

✴️ @AI_Python_EN

Course 3 is less than 24 hours away! Andrew and Laurence introduce Shakespearean text generation, the main NLP application you’ll build in the course:

deeplearning.ai

✴️ @AI_Python_EN

https://github.com/SidharthRai/Regression-and-Technical-Analysis-of-Stock-Market

Regression and Technical Analysis of Stock Market

by Sidharth Rai

Link to Project Report: http://bit.ly/Analysis_Project

This project is based on a complete mathematical analysis using Technical Analysis which is used to calculate the unknown patterns in the behaviors and changes of Stock Prices over a period of the month because of wide acceptability of Equity-based market.

• Stars - 6
• Forks - 5

This is my research project too, find my research work on https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3356304

thanks to :Sidharth Rai

Course 3 of the deeplearning.ai TensorFlow Specialization is now available on Coursera! You’ll learn how to process text using tokenization and train LSTMs to create original poetry. You can enroll in the Specialization for $49/month or audit for free: http://bit.ly/2ZkmPRY
✴️ @AI_Python_EN

Recent developments in pre-trained context based embeddings like BERT, GPT has already pushed the boundaries in NLP. Now there is a new entrant to the list - XLNet

XLNet - Generalized Autoregressive Pretraining for Language Understanding is outperforming BERT and achieving SOTA results on multiple NLP tasks.

Code : https://lnkd.in/fp8rRVc
Paper : https://lnkd.in/fb5FGUh

#nlp #deeplearning
✴️ @AI_Python_EN

This is a very dense and highly mathematical A-Z overview of text mining. The book is not one for the beach but is packed with useful information and practical tips.

Many working in text mining would probably find it a useful reference. It may also be of interest to marketing science people who use the results of text mining in advanced analytics or who are involved in marketing research R&D.

The author, Charu C. Aggarwal, is a Distinguished Research Staff Member at the IBM T. J. Watson Research Center. He has published more than 350 papers in refereed conferences and journals on data mining topics.

Though his writing style is no-nonsense, Aggarwal's enthusiasm for the topic comes through loud and clear. It is telling that in this and others of his I've read he uses the term "AI" sparingly. The book is not a hyped sales pitch in disguise. Far from it.

https://www.springer.com/gp/book/9783319735306

✴️ @AI_Python_EN

Text mining and Natural Language Processing are highly specialized fields with many specializations within. I'm not an expert in these areas but have read up on them because of the nature my work.

While I would hesitate to call them statistics, familiar statistical methods do play a role and a statistician completely new to these fields probably would not find them bizarre. The same holds for AI. IMO.

Here are a few other books on these subjects I've found helpful if sometimes challenging:

- Foundations of Computational Linguistics (Hausser)
- The Handbook of Computational Linguistics (Clark et al.)
- Sentiment Analysis: Mining Opinions, Sentiments, and Emotions (Liu)
- Neural Network Methods in Natural Language Processing (Goldberg)
- Social Media Intelligence (Moe and Schweidel)
- Natural Language Processing for Social Media (Farzindar and Inkpen)
- Machine Translation (Poibeau)
- Text Mining in Practice with R (Kwartler)

✴️ @AI_Python_EN

One of the BEST #MachineLearning Glossary by Google

It will definitely come in handy - https://lnkd.in/gNiE9JT

Link to learn more about Machine Learning:

✅ Course 1 : A comprehensive Learning Path to become Data Scientist in 2019
Link : https://bit.ly/2HOthei

✅ Course 2 : Experiments with Data
Link : https://bit.ly/2HQuQbw

✅ Course 3 : Python for Data Science
Link : https://bit.ly/2HOG5RG

✅ Course 4 : Twitter Sentiments Analysis
Link : https://bit.ly/2HR8O8A

✅ Course 5 : Creating Time Series Forecast with Python
Link : https://bit.ly/2XniU6r

✅ Course 6 : A comprehensive path for learning Deep Learning in 2019
Link : https://bit.ly/2HO1VVJ

✅ Course 7 : Loan Prediction Practice problem
Link : https://bit.ly/2IcynQl

✅ Course 8 : Big mart Sales Problem using R
Link : https://bit.ly/2JUlZIb

#announcements #datascientist #machinelearning #datascience #artificialintelligence

✴️ @AI_Python_EN

If you're interested in learning a simple and powerful data cleaning framework for your work, have a look at this post.

Data cleaning takes nearly 60 - 70 % of our time and all the fancy models & visualizations are created after slogging hours of cleaning the data.

If you need a shiny report at the end which will answer all the business questions, you have to go through the time consuming process for yourself.

Real world data is not as clean as kaggle datasets but still you can find datasets which are not ready made for analysis in UCI or Kaggle to work on.

Try these things on a dataset this weekend and share your work with the community.

Link to first post <- https://lnkd.in/fQmem8d

Link to the second post <- https://lnkd.in/ffrQqgC

✴️ @AI_Python_EN

When to Trust Your Model: Model-Based Policy Optimization

Janner et al.: https://lnkd.in/eTmBjA9

#ArtificialIntelligence #DeepLearning #ReinforcementLearning

✴️ @AI_Python_EN

open sourcing PyRobot, a lightweight, high-level interface that lets #AI researchers get up and running with #robotics experiments in just hours. No specialized robotics expertise needed! https://ai.facebook.com/blog/open-sourcing-pyrobot-to-accelerate-ai-robotics-research/

✴️ @AI_Python_EN

11 things I learned from the Machine Learning for Coders course at fastdotai"
https://medium.com/yottabytes/11-things-i-learned-from-the-machine-learning-for-coders-course-at-fast-ai-799468b089bc?source=friends_link&sk=337416e814280d88e7bfad994cac8533
#machinelearning #datascience #ml #python #bigdata

✴️ @AI_Python_EN