Deep Learning, Editorial, Programming

An in-depth tutorial on convolutional neural networks (CNNs) with Python

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. …

Data Science, Editorial, Machine Learning

For the past year, we have looked at over 2,000 laptops [8] and picked what we consider to be the best laptops for machine learning, data science, and deep learning for every budget — future proof your AI rig!

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. …

Machine Learning, Editorial, Programming

Diving into decision trees in machine learning (ML) with Python

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. …

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

An introductory tutorial to linear algebra for machine learning (ML) and deep learning with sample code implementations in Python

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

What is new in the AI world, the release of our book, and our monthly editorial picks

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. …

Data Science, Editorial, Programming

An in-depth tutorial on principal component analysis (PCA) with mathematics and Python coding examples

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. …

Programming, Editorial, Tutorial

An in-depth tutorial on how to use Google Colab with Python, along with Colab’s tips, tricks, and FAQ

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

Building a machine learning recommendation system tutorial using Python and collaborative filtering for a Netflix use case.

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. …