🌟

An Introduction to Machine Learning by Miroslav Kubat

FREE ebook on Machine Learning

 An introduction to machine learning book will get you started with various data science techniques such as decision trees, performance evaluation, among others. It also covers sub-categories such as unsupervised learning, reinforcement learning, and neural networks. Learners can obtain a detailed understanding of various classifiers and algorithms from 17 chapters, thereby making it a good read during the lockdown.

https://link.springer.com/book/10.1007%2F978-3-319-63913-0
#machineLearning #DataScience #eBook

🌟

All of Statistics by Larry Wasserman
A Concise Course in Statistical Inference

FREE ebook on Statistics for Machine Learning

 A proper grasp of statistics is essential for any machine learning enthusiast to succeed in the competitive domain. Consequently, one should focus more on statistics than on the latest fancy techniques. The book — All of Statistics — consists of 24 chapters and covers every topic right from probability to statistical inference and statistical models and methods.

https://link.springer.com/content/pdf/10.1007%2F978-0-387-21736-9.pdf
#machineLearning #DataScience #eBook #statistics

Introduction To Time Series And Forecasting
by Peter J. BrockwellRichard A. Davis

FREE eBook

 Time series analysis has gain popularity due to its use cases in financial data, especially, in companies’ stock prediction, fraud detection in transactions, and more. Besides, it is now becoming an essential technique in data science due to the rise of streaming analytics in numerous business operations. Obtaining real-time insights while also comparing with the historical trends allow companies to quickly make informed decisions. 

The book includes 11 chapters on a wide range of time series techniques such as nonstationary and seasonal time series models, multivariate time series, state-space models, and forecasting methods.

https://link.springer.com/content/pdf/10.1007%2F978-3-319-29854-2.pdf
#machineLearning #DataScience #eBook #statistics

🌟

Principles Of Data Mining
by Principles of Data Mining

 With more than 2.3 million downloads, this is one of the most popular data science books. The process of data mining has increasingly become essential for businesses to achieve rapidly grow by making decisions based on insights. Therefore, this book includes all principles for data mining to discover patterns in a colossal amount of data. Designed to help even the beginners, it covers an introduction to classification like Naive Bayes, Nearest Neighbour, Decision Tree, among others, along with detailed explanations.

https://link.springer.com/content/pdf/10.1007%2F978-1-4471-7307-6.pdf
#machineLearning #DataScience #eBook #statistics

🌟

Neural Networks And Deep Learning
by Charu C. Aggarwal

FREE eBook

 It is a comprehensive book on deep learning for every aspirant as well as working professionals. The book covers both classical as well as the latest models in deep learning, thereby explaining the difference between several techniques and their effectiveness. The book also focuses on the right practices for AI agents to generalise. Besides, it has lessons on various neural networks like RNN, CNN, DRL, other advanced topics in deep learning.

https://link.springer.com/content/pdf/10.1007%2F978-3-319-94463-0.pdf
#machineLearning #DataScience #eBook #deepLearning #neuralNetworks

🌟

Recommender Systems
by Charu C. Aggarwal

Free eBook

 Today, companies are delivering personalised experiences to their users for enhancing customer experience. Such practices are widely common on social media platforms and e-commerce websites, however, now it is being democratised across all business to increase conversion rate. The book has categorised the learning in three sub-section: algorithms and evaluation, recommendations in specific domains and contexts, advanced topics and applications. 

https://link.springer.com/content/pdf/10.1007%2F978-3-319-29659-3.pdf
#machineLearning #DataScience #eBook #algorithm

Computer Vision
Algorithms and Applications
by Richard Szeliski

Free eBook

 Computer vision technology is playing a crucial role in data science by expediting various processes such as analysing medical imaging, assisting in the development of self-driving cars, and determining defects in manufacturing processes. It can be applied in endless processes to simplify the life of humans. However, there are various challenges in computer vision technology while interpreting 3D images as well as delivers biased results. This book explains the ins and outs of the computer vision along with lessons on various techniques.

https://link.springer.com/content/pdf/10.1007%2F978-1-84882-935-0.pdf
#machineLearning #DataScience #eBook #algorithm #computerVision

Even More Python for Beginners: Data Tools by Microsoft

 Aspiring data-science and machine-learning developers now have more Microsoft-made free video tutorials to learn how to build software in Python, one of today's most popular and versatile programming languages.
The new More Python for Beginners series consists of 20 videos that run between two minutes and 15 minutes each. It covers working with files, lambdas  or 'anonymous functions', and object-oriented programming, and each tutorial is followed by a short demo video. The tutors also introduce some newer functionality to support asynchronous development through async/await.

https://www.youtube.com/playlist?list=PLlrxD0HtieHhHnCUVtR8UHS7eLl33zfJ-
#course #python #beginners

​​Cross-Lingual Ability of Multilingual BERT: An Empirical Study to #ICLR2020

In this work, the authors provide a comprehensive study of the contribution of different components in multilingual #BERT (M-BERT) to its cross-lingual ability.
They study the impact of linguistic properties of the languages, the architecture of the model, and the learning objectives. The experimental study is done in the context of three typologically different languages – #Spanish, #Hindi, & #Russian – & using two conceptually different #NLP tasks, textual entailment & #NER.

Also, they construct a new corpus – Fake-English (#enfake), by shifting the Unicode of each character in English Wikipedia text by a large constant so that there is strictly no character overlap with any other Wikipedia text.
And, in this work, they consider Fake-English as a different language.

Among their key conclusions are the fact that the lexical overlap between languages plays a negligible role in the cross-lingual success, while the depth of the network is an integral part of it.

paper: https://arxiv.org/abs/1912.07840

#DS #ML #NN #ebooks

https://blog.paralleldots.com/data-science/24-best-and-free-books-to-understand-machine-learning/

In python 3.9, PEP-616 introduced str.removeprefix and str.removesuffix methods:

'abcd'.removeprefix('ab')
# 'cd'

'abcd'.removeprefix('fg')
# 'abcd'

The implementation is simple (it's implemented on C, of course, but the idea is the same):

def removeprefix(self: str, prefix: str) -> str:
if self.startswith(prefix):
return self[len(prefix):]
return self

​​Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer

tl;dr:
- 11 billion parameters
- encoder-decoder models generally outperformed “decoder-only” language models
- fill-in-the-blank-style denoising objectives worked best;
- the most important factor was the computational cost;
- training on in-domain data can be beneficial but that pre-training on smaller datasets can lead to detrimental overfitting;
- multitask learning could be close to competitive with a pre-train-then-fine-tune approach but requires carefully choosing how often the model is trained on each task

The model can be fine-tuned on smaller labeled datasets, often resulting in (far) better performance than training on the labeled data alone.
Present a large-scale empirical survey to determine which transfer learning techniques work best and apply these insights at scale to create a new model that we call the T5. Also, introduce a new open-source pre-training dataset, called the Colossal Clean Crawled Corpus (C4).

The T5 model, pre-trained on C4, achieves SOTA results on many NLP benchmarks while being flexible enough to be fine-tuned to a variety of important downstream tasks.


blog post: https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html
paper: https://arxiv.org/abs/1910.10683
github (with pre-trained models): https://github.com/google-research/text-to-text-transfer-transformer
colab notebook: https://colab.research.google.com/github/google-research/text-to-text-transfer-transformer/blob/master/notebooks/t5-trivia.ipynb

#nlp #transformer #t5

Interesting paper bout reproducibility in AI/ML from Dr. Edward Raff is a Chief Scientist at Booz Allen Hamilton. He analyzed 255 papers, and successfully reproduce 162 from them.

A 62% success rate is higher than many meta-analyses from other sciences, and I suspect my 62% number is lower than reality

Interesting facts:
1. Having fewer equations per page makes a paper more reproducible.
2. Empirical papers may be more reproducible than theory-oriented papers.
3. Sharing code is not a panacea
4. Having detailed pseudo code is just as reproducible as having no pseudo code.
5. Creating simplified example problems do not appear to help with reproducibility.
6: Please, check your email (papers of people who answer on emails is more reproducible)

https://thegradient.pub/independently-reproducible-machine-learning/

Leave a comment on how do you feel about this.

https://github.com/ignani/PythonMLDataScience

Have just uploaded some samples. Will keep adding as and when I get some free time. You can use it for learning.

Let me know what view. 😊