Forwarded from DLeX: AI Python (Farzadπ¦
πππ¦π»)
Innovation Nation: AI godfathers gave Canada an early edge β but we could end up being left in the dust
"Canada is hanging on to the lead by 'our fingernails' as the gold rush to commercialize artificial intelligence goes global"
By James McLeod: https://lnkd.in/emxjPNS
#artificialintelligence #business #deeplearning
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
"Canada is hanging on to the lead by 'our fingernails' as the gold rush to commercialize artificial intelligence goes global"
By James McLeod: https://lnkd.in/emxjPNS
#artificialintelligence #business #deeplearning
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Week 2 of AI for Everyone is all about identifying and building AI projects. Check out what youβll learn:
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
In the context of algorithm fairness in AI. From the O'Reilly Data Show podcast, Sharad Goel says: "You need domain expertise. There's no silver bullet. There's no black box you stick your algorithm into and it gives you thumbs up or down. It always depends on domain and context".
Examples in the podcast and paper are from loan approvals and the elusive idea of "fairness".
It's encouraging that people are socializing the challenges and limitations of data driven approaches and the role domain context plays in it.
This also has ramifications for organizations trying to create effective analytics strategies: it's hard delegate analytics because the needed domain context originates outside of the analytics space (which also explains why outsourcing analytics/data science offshore has not been successful).
Finally, on the idea of fairness, it's worth pointing out this is a bit if old news. Thomas Lumley points out in a similar article "This is old news in medical diagnostics, but appears not to have been considered in some other areas".
O'Reilly Data Show - O'Reilly Media Podcast -
https://lnkd.in/e9ryTZc
#analytics #datascience #machinelearning #statistics
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Examples in the podcast and paper are from loan approvals and the elusive idea of "fairness".
It's encouraging that people are socializing the challenges and limitations of data driven approaches and the role domain context plays in it.
This also has ramifications for organizations trying to create effective analytics strategies: it's hard delegate analytics because the needed domain context originates outside of the analytics space (which also explains why outsourcing analytics/data science offshore has not been successful).
Finally, on the idea of fairness, it's worth pointing out this is a bit if old news. Thomas Lumley points out in a similar article "This is old news in medical diagnostics, but appears not to have been considered in some other areas".
O'Reilly Data Show - O'Reilly Media Podcast -
https://lnkd.in/e9ryTZc
#analytics #datascience #machinelearning #statistics
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
π‘ What is multi-armed bandit testing and why is it useful?
Multi-armed bandit (or simply "bandit") testing is similar to multivariate and A/B testing, but the sampling distribution for variants change gradually over time as feedback is received.
For example, with traditional A/B tests, we could test 2 email subject lines: A and B. We would initially send out emails to 200 customers, sending 100 A variations and 100 B variations. After some set period of time, say 24 hours, we would observe which email variant was opened by more customers. We would then send that variant to all customers moving forward.
With bandit testing, we would set some learning rate for the distribution of variants to change over time. Perhaps 60 customers opened the A variant emails and only 50 customers opened the B variant emails. We could then shift the distribution from (50% A, 50% B) to (55% A, 45% B) for the next round of emails.
Using this approach, we can continuously monitor the response from our audience and shift our actions accordingly. This is particularly useful in marketing or any industry where people's preferences and opinions may change rapidly since it continuously tests and learns preferences and can adapt very quickly.
#datascience #dsdj #multiarmedbandit
#QandA
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Multi-armed bandit (or simply "bandit") testing is similar to multivariate and A/B testing, but the sampling distribution for variants change gradually over time as feedback is received.
For example, with traditional A/B tests, we could test 2 email subject lines: A and B. We would initially send out emails to 200 customers, sending 100 A variations and 100 B variations. After some set period of time, say 24 hours, we would observe which email variant was opened by more customers. We would then send that variant to all customers moving forward.
With bandit testing, we would set some learning rate for the distribution of variants to change over time. Perhaps 60 customers opened the A variant emails and only 50 customers opened the B variant emails. We could then shift the distribution from (50% A, 50% B) to (55% A, 45% B) for the next round of emails.
Using this approach, we can continuously monitor the response from our audience and shift our actions accordingly. This is particularly useful in marketing or any industry where people's preferences and opinions may change rapidly since it continuously tests and learns preferences and can adapt very quickly.
#datascience #dsdj #multiarmedbandit
#QandA
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
14 NLP Research breakthroughs you can apply to your business:
1. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2. Sequence Classification with Human Attention
3. Phrase-Based & Neural Unsupervised Machine Translation
4. What you can cram into a single vector: Probing sentence embeddings for linguistic properties
5. SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
6. [ELMo] Deep contextualized word representations
7. Meta-Learning for Low-Resource Neural Machine Translation
8. Linguistically-Informed Self-Attention for Semantic Role Labeling
9. A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
10. Know What You Donβt Know: Unanswerable Questions for SQuAD
11. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
12. Universal Language Model Fine-tuning for Text Classification
13. Improving Language Understanding by Generative Pre-Training
14. Dissecting Contextual Word Embeddings: Architecture and Representation
Source: TopBot https://lnkd.in/eCYFvFE
#nlp #deeplearning
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
1. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2. Sequence Classification with Human Attention
3. Phrase-Based & Neural Unsupervised Machine Translation
4. What you can cram into a single vector: Probing sentence embeddings for linguistic properties
5. SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
6. [ELMo] Deep contextualized word representations
7. Meta-Learning for Low-Resource Neural Machine Translation
8. Linguistically-Informed Self-Attention for Semantic Role Labeling
9. A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
10. Know What You Donβt Know: Unanswerable Questions for SQuAD
11. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
12. Universal Language Model Fine-tuning for Text Classification
13. Improving Language Understanding by Generative Pre-Training
14. Dissecting Contextual Word Embeddings: Architecture and Representation
Source: TopBot https://lnkd.in/eCYFvFE
#nlp #deeplearning
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Here's a comprehensive learning path for any person wanting to get into the field of deep learning. This path contains plenty of resources, links, ideas and suggestions to get you on your way! Also download the below infographic - A very handy resource for every data science professional.
https://lnkd.in/f3yVDkW
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
https://lnkd.in/f3yVDkW
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Time Series forecasting & modeling plays an important role in data analysis. The best way to learn #TimeSeries techniques is by applying them on time series data!
Here's a really cool #dataset where you need to
#forecast the traffic for a startup's product. Close to 10,500 data scientists have taken this challenge - can you climb up the leaderboard?https://lnkd.in/fyZiCJt
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Here's a really cool #dataset where you need to
#forecast the traffic for a startup's product. Close to 10,500 data scientists have taken this challenge - can you climb up the leaderboard?https://lnkd.in/fyZiCJt
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
François Chollet
The complaints "Python is slow" or "Python is unsafe" seem misguided. The point of Python isn't to be fast or safe, it's to be flexible and hackable, and to interface well with everything else. It has become successful by serving as a frontend from which to call other libraries.
#Python is more of an interface than it is a development language. It's a UX.
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
The complaints "Python is slow" or "Python is unsafe" seem misguided. The point of Python isn't to be fast or safe, it's to be flexible and hackable, and to interface well with everything else. It has become successful by serving as a frontend from which to call other libraries.
#Python is more of an interface than it is a development language. It's a UX.
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Yann LeCun
Video of my talk at the Institute of Advanced Studies workshop "Deep Learning: Alchemy or Science?", organized by Sanjeev Arora Friday Feb 22, 2019. The audience was very diverse, so I focused on the early history and dynamics of ideas in neural..
π The epistemology of Deep Learning"
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Video of my talk at the Institute of Advanced Studies workshop "Deep Learning: Alchemy or Science?", organized by Sanjeev Arora Friday Feb 22, 2019. The audience was very diverse, so I focused on the early history and dynamics of ideas in neural..
π The epistemology of Deep Learning"
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Google Doubles Down On Spammers With #TensorFlow. #BigData #Analytics #MachineLearning #DataScience #AI #NLProc #IoT #IIoT #PyTorch #Python #RStats #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #TransferLearning
π http://bit.ly/2U4ZSAf
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
π http://bit.ly/2U4ZSAf
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Knowing that people judge you by your books I picked out this selection for our new IKEA book shelves. Now Iβm just waiting for any statistician to come visit.
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Forwarded from DLeX: AI Python (Farzadπ¦
πππ¦π»)
β¨οΈ Free Self-Study Books on Mathematics, Machine Learning & Deep Learning
πΆ1. Matrix Computations
β Free Book: Download here
πΆ 2. A Probabilistic Theory of Pattern Recognition
π Free Book: Download here
β 3. Advanced Engineering Mathematics
π Free Book: Download here
β 4. Probability and Statistics Cookbook
Free Book: Download here
Machine Learning & Deep Learning Books
β‘οΈ 1. An Introduction to Statistical Learning (with applications in R)
π Free Book: Download here
β‘οΈ 2. Probabilistic Programming and Bayesian Methods for Hackers
π Free Book: Download here
β‘οΈ3. The Elements of Statistical Learning
π Free Book: Download here
β‘οΈ4. Bayesian Reasoning and Machine Learning
π Free Book: Download here
βοΈ@AI_Python
βοΈ@Data_Experts
βοΈ 5. Information Theory, Inference, and Learning Algorithms
π Free Book: Download here
βοΈ 6. Deep Learning
πFree Book: Download here
π 7. Neural Networks and Deep Learning
π Free Book: Download here
π 8. Supervised Sequence Labelling with Recurrent Neural Networks
πFree Book: Download here
π 9. Reinforcement Learning: An Introduction
π Free Book: Download here
#Ϊ©ΨͺΨ§Ψ¨ #ΩΩΨ΄_Ω Ψ΅ΩΩΨΉΫ #ΫΨ§Ψ―Ϊ―ΫΨ±Ϋ_ΨΉΩ ΫΩ #ΫΨ§Ψ―Ϊ―ΫΨ±Ϋ_ΨͺΩΩΫΨͺΫ #Ψ’Ω ΩΨ²Ψ΄ #Ψ’Ω Ψ§Ψ± #Ψ§ΨΨͺΩ Ψ§Ω
βοΈ@AI_Python
βοΈ@Data_Experts
πΆ1. Matrix Computations
β Free Book: Download here
πΆ 2. A Probabilistic Theory of Pattern Recognition
π Free Book: Download here
β 3. Advanced Engineering Mathematics
π Free Book: Download here
β 4. Probability and Statistics Cookbook
Free Book: Download here
Machine Learning & Deep Learning Books
β‘οΈ 1. An Introduction to Statistical Learning (with applications in R)
π Free Book: Download here
β‘οΈ 2. Probabilistic Programming and Bayesian Methods for Hackers
π Free Book: Download here
β‘οΈ3. The Elements of Statistical Learning
π Free Book: Download here
β‘οΈ4. Bayesian Reasoning and Machine Learning
π Free Book: Download here
βοΈ@AI_Python
βοΈ@Data_Experts
βοΈ 5. Information Theory, Inference, and Learning Algorithms
π Free Book: Download here
βοΈ 6. Deep Learning
πFree Book: Download here
π 7. Neural Networks and Deep Learning
π Free Book: Download here
π 8. Supervised Sequence Labelling with Recurrent Neural Networks
πFree Book: Download here
π 9. Reinforcement Learning: An Introduction
π Free Book: Download here
#Ϊ©ΨͺΨ§Ψ¨ #ΩΩΨ΄_Ω Ψ΅ΩΩΨΉΫ #ΫΨ§Ψ―Ϊ―ΫΨ±Ϋ_ΨΉΩ ΫΩ #ΫΨ§Ψ―Ϊ―ΫΨ±Ϋ_ΨͺΩΩΫΨͺΫ #Ψ’Ω ΩΨ²Ψ΄ #Ψ’Ω Ψ§Ψ± #Ψ§ΨΨͺΩ Ψ§Ω
βοΈ@AI_Python
βοΈ@Data_Experts
CS294-158 Deep Unsupervised Learning Spring 2019
https://sites.google.com/view/berkeley-cs294-158-sp19/home
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
https://sites.google.com/view/berkeley-cs294-158-sp19/home
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
How Machine Learning and AI are Changing eSports and Knowledge Itself
#Automation #AI #MachineLearning https://medium.com/swlh/how-machine-learning-and-ai-are-changing-esports-and-knowledge-itself-b4d977473cc1?source=rss-------8-----------------artificial_intelligence
#Automation #AI #MachineLearning https://medium.com/swlh/how-machine-learning-and-ai-are-changing-esports-and-knowledge-itself-b4d977473cc1?source=rss-------8-----------------artificial_intelligence
Medium
How Machine Learning and AI are Changing eSports and Knowledge Itself
AI, Machine Learning, and eSports are all burgeoning industries. Hereβs how theyβre changing things.
I may be wrong, but I get the impression that some data science people believe regression comes in just two flavors - OLS linear and binary logistic.
Setting aside the relationship between neural nets and regression, and that VAR, GARCH, Structural Equation Models and numerous other statistical models are really forms of regression, I have no idea how many kinds of "regression" are in common use.
"Dozens" would probably be an underestimate. There are countless other types which are used infrequently but essential in certain circumstances, like a fifth pitch in baseball.
Moreover, there is usually more than one way to estimate most statistical models. It's not unusual for a statistician to run one kind of regression model several ways with maximum likelihood estimation (MLE) and Bayesian alternatives, for example.
We have a BIG regression decision tree, and our choices are seldom inconsequential.
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Setting aside the relationship between neural nets and regression, and that VAR, GARCH, Structural Equation Models and numerous other statistical models are really forms of regression, I have no idea how many kinds of "regression" are in common use.
"Dozens" would probably be an underestimate. There are countless other types which are used infrequently but essential in certain circumstances, like a fifth pitch in baseball.
Moreover, there is usually more than one way to estimate most statistical models. It's not unusual for a statistician to run one kind of regression model several ways with maximum likelihood estimation (MLE) and Bayesian alternatives, for example.
We have a BIG regression decision tree, and our choices are seldom inconsequential.
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
image_2019-02-26_17-58-34.png
682.3 KB
You know what a neural network is, and you know what a ML project workflow looks like. Now how do you implement it throughout your entire company? Week 3 of AI for Everyone will walk you through it:
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
image_2019-02-26_22-02-43.png
789.8 KB
Left: how you would plot the Xception architecture in a paper.
Right: how you would implement it with the Functional API (that's the entire code).
1:1 match between how you think about it and how you write it.
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
Right: how you would implement it with the Functional API (that's the entire code).
1:1 match between how you think about it and how you write it.
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
How does Google Translate's AI work? https://youtu.be/sIoHFPGOY0I
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv
β΄οΈ @AI_Python_EN
βοΈ @AI_Python
π£ @AI_Python_arXiv