Publishing the Best of Tech, Science, and Engineering | Editorial → https://towardsai.net/p/editorial | Subscribe→ https://towardsai.net/subscribe — @Towards_AI
Source: Derivative from original, Photo by Patrick Robert Doyle on Unsplash | Best Machine Learning Books | Machine Learning
Source: Derivative from original, Photo by Patrick Robert Doyle on Unsplash | Best Machine Learning Books | Machine Learning
Source: Derivative from original, Photo by Patrick Robert Doyle on Unsplash

Machine Learning, Editorial

Nowadays, we know that machine learning and its applications have become inevitable [5] for most (if not all) businesses. Hence, there is a surge of proficient machine learning engineers.

We know that machine learning can be intimidating if you are just starting your career in this domain. Therefore, if you plan to move into the scientific field of machine learning, you may find yourself overwhelmed with the wide variety of books related to machine-learning available online.

In this article, we will list some of the best books on machine learning. …


A neural network, in shape of a brain with a gradient background | Convolutional Neural Networks (CNNs) Tutorial with Python
A neural network, in shape of a brain with a gradient background | Convolutional Neural Networks (CNNs) Tutorial with Python
Source: Pixabay

Deep Learning, Editorial, Programming

Author(s): Saniya Parveez, Roberto Iriondo

This tutorial’s code is available on Github and its full implementation as well on Google Colab.

Table of Contents

  1. Introduction
  2. Network Architecture
  3. Convolution
  4. Convolutional Layers
  5. Pooling Layers/Subsampling layers
  6. Stride
  7. Fully Connected Layer
  8. Non-Linear Layers
  9. Python Implementation of Convolutional Neural Networks (CNNs)
  10. Hyperparameters for CNNs
  11. Regularization Methods in CNNs
  12. Conclusion
  13. Resources
  14. References

📚 Check out our editorial recommendations on the best machine learning books. 📚

Introduction

Yann LeCun and Yoshua Bengio introduced convolutional neural networks in 1995 [1], also known as convolutional networks or CNNs. A CNN is a particular kind of multi-layer neural network [2] to process data with an apparent, grid-like topology. The base of its network bases on a mathematical operation called convolution. Fundamentally, machine learning algorithms use matrix multiplication, but in contrast, CNNs use convolutions in place of matrix multiplications at least in one layer — a convolution is a specialized kind of linear operation. …


Source: Photo by Christian Wiediger on Unsplash performance machine learning, deep learning, data science laptop
Source: Photo by Christian Wiediger on Unsplash performance machine learning, deep learning, data science laptop
Source: Photo by Christian Wiediger on Unsplash

Data Science, Editorial, Machine Learning

Last updated December 1, 2020

Machine learners, deep learning practitioners, and data scientists are continually looking for the edge on their performance-oriented devices. That’s why we looked at over 2,000 laptops to bring you what we consider the best laptops for your projects on machine learning, deep learning, and data science.

We will continuously update this resource with powerful and more performant laptops for every budget as technology continues to evolve to bring you the best suggestions for your machine learning, data science, and deep learning projects and adventures.

Our mailbox is full of emails from AI enthusiasts asking us for the best laptops for AI projects. That’s why we decided to make this list. If you have any suggestions to add to the list, please let us know by emailing us at pub@towardsai.net. …


Decision Trees in Machine Learning (ML) with Python | Source: Image by Bela Geletneky from Pixabay
Decision Trees in Machine Learning (ML) with Python | Source: Image by Bela Geletneky from Pixabay
Source: Image by Bela Geletneky from Pixabay

Machine Learning, Editorial, Programming

Author(s): Saniya Parveez, Roberto Iriondo

This tutorial’s code is available on Github and its full implementation as well on Google Colab.

Table of Contents

  1. What is a Decision Tree?
  2. Decision Tree Example
  3. Building a Decision Tree
  4. Node Impurity
  5. Entropy
  6. Gini
  7. Overfitting in Decision Tree Learning
  8. Pruning
  9. Advantages and Disadvantages of Decision-tree-based Classification
  10. Code Implementation
  11. Advanced Decision Trees
  12. Conclusion
  13. Resources
  14. References

What is a Decision Tree?

A decision tree is a vital and popular tool for classification and prediction problems in machine learning, statistics, data mining, and machine learning [4]. It describes rules that can be interpreted by humans and applied in a knowledge system such as databases. …


Figure 1: A three-dimensional Euclidean space used to represent solutions of linear equations. Image is a derivative from vec
Figure 1: A three-dimensional Euclidean space used to represent solutions of linear equations. Image is a derivative from vec
Figure 1: A three-dimensional Euclidean space used to represent solutions of linear equations [1] [2]. Image is a vector derivative from “High-dimensional Simplexes for Supermetric Search” by Richard Connor, Lucia Vadicamo, and Fausto Rabitti [3].

Deep Learning, Editorial, Machine Learning, Mathematics, Programming, Tutorial

Author(s): Saniya Parveez, Roberto Iriondo

This tutorial’s code is available on Github and its full implementation as well on Google Colab.

Table of Contents

  1. Introduction
  2. Linear Algebra in Machine Learning and Deep Learning
  3. Matrix
  4. Vector
  5. Matrix Multiplication
  6. Transpose Matrix
  7. Inverse Matrix
  8. Orthogonal Matrix
  9. Diagonal Matrix
  10. Transpose Matrix and Inverse Matrix in Normal Equation
  11. Linear Equation
  12. Vector Norms
  13. L1 norm or Manhattan Norm
  14. L2 norm or Euclidean Norm
  15. Regularization in Machine Learning
  16. Lasso
  17. Ridge
  18. Feature Extraction and Feature Selection
  19. Covariance Matrix
  20. Eigenvalues and Eigenvectors
  21. Orthogonality
  22. Orthonormal Set
  23. Span
  24. Basis
  25. Principal Component Analysis (PCA)
  26. Matrix Decomposition or Matrix Factorization
  27. Conclusion
  28. Resources
  29. References

Introduction

The foundation of machine learning and deep learning systems wholly base upon mathematics principles and concepts. It is imperative to understand the fundamental foundations of mathematical principles. During the baseline and building of the model, many mathematical concepts like the curse of dimensionality, regularization, binary, multi-class, ordinal regression, and others must be artistic in mind. …


News, Newsletter

If you have trouble reading this email, see it on a web browser.

Happy Monday, Towards AI family! To start your week with a smile, we recommend you to check out “Superheroes of Deep Learning Vol 1: Machine Learning Yearning” by Falaah Arif Khan and Professor Zachary Lipton, an exciting, hilarious, and educational comic for everyone who is or has worked with data in the past.

If you are into research, NeurIPS recently posted its findings during the 2020 paper reviewing process, with some insights on the submission and historical data on primary subject areas, acceptance rate, ratings, and so on for the past two years. …


Image for post
Image for post
Source: Derivative from original by Radek Grzybowski on Unsplash

Data Science, Editorial, Programming

Author(s): Saniya Parveez, Roberto Iriondo

This tutorial’s code is available on Github and its full implementation as well on Google Colab.

Table of Contents

  1. Introduction
  2. Curse of Dimensionality
  3. Dimensionality Reduction
  4. Correlation and its Measurement
  5. Feature Selection
  6. Feature Extraction
  7. Linear Feature Extraction
  8. Principal Component Analysis (PCA)
  9. Math behind PCA
  10. How does PCA work?
  11. Applications of PCA
  12. Implementation of PCA with Python
  13. Conclusion

Introduction

When implementing machine learning algorithms, the inclusion of more features might lead to worsening performance issues. Increasing the number of features will not always improve classification accuracy, which is also known as the curse of dimensionality. …


Laptop displaying Google Colab by Google, image is a derivative from original by Bongkarn Thanyakij on Pexels.
Laptop displaying Google Colab by Google, image is a derivative from original by Bongkarn Thanyakij on Pexels.
Source: Derivative from original by Bongkarn Thanyakij on Pexels

Programming, Editorial, Tutorial

Author(s): Saniya Parveez, Roberto Iriondo

This tutorial’s code is available on Github and its full implementation as well on Google Colab.

Table of Contents

  1. Introduction
  2. Why We Use Google Colab?
  3. Start Google Colab
  4. Uploading a Notebook from Github
  5. Uploading Data from Kaggle
  6. Read Files from Google Drive
  7. Setting up Hardware Accelerator GPU for Runtime
  8. Clone a GitHub Repository to Google Drive
  9. Colab Magic
  10. Plotting
  11. TPU (Tensor Processing Unit) in Google Colab
  12. Conclusion

Introduction

Google Colab is a project from Google Research, a free, Jupyter based environment that allows us to create Jupyter [programming] notebooks to write and execute Python [1](and other Python-based third-party tools and machine learning frameworks such as Pandas, PyTorch, Tensorflow, Keras, Monk, OpenCV, and others) in a web browser. …


Machine Learning, Editorial, Programming, Tutorial

Author(s): Saniya Parveez, Roberto Iriondo

What is a Recommendation System?

A recommendation system generates a compiled list of items in which a user might be interested, in the reciprocity of their current selection of item(s). It expands users’ suggestions without any disturbance or monotony, and it does not recommend items that the user already knows.

For instance, the Netflix recommendation system offers recommendations by matching and searching similar users' habits and suggesting movies that share characteristics with films that users have rated highly.

In this tutorial, we will dive into building a recommendation system for Netflix.

This tutorial’s code is available on Github and its full implementation as well on Google Colab.


News, Newsletter

If you have trouble reading this email, see it on a web browser.

Work in the AI field is moving forward very quickly. Today Papers with Code announced their partnership with arXiv, where code links are now shown on arXiv articles, and authors can submit code through arXiv, making it a great addition to avid researchers and practitioners.

NeurIPS also announced a cool challenge, the 2020 ML Reproducibility Challenge sponsored by Papers with Code, encouraging people who work with ML to participate (including enthusiasts!). If you’d like to learn more, check out their announcement, it sounds pretty neat.

In other news, if you are into reinforcement learning, we encourage you to check out MineRL — their research group just announced the extension of their competition till February 2021. So if you’d like to build some sample-efficient AI agents in Minecraft, definitely check them out! …

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store