Collaborating Authors

Mathematical & Statistical Methods

Machine Learning for Signal Processing: Data Science, Algorithms, and Computational Statistics: Little, Max A.: 9780198714934: Books


"This book provides an excellent pathway for gaining first-class expertise in machine learning. It provides both the technical background that explains why certain approaches, but not others, are best practice in real world problems, and a framework for how to think about and approach new problems. I highly recommend it for people with a signal processing background who are seeking to become an expert in machine learning." With this book, Prof. Little has taken an important step in unifying Âmachine learning and signal processing. As a whole, this book covers many topics, new and old, that are important in their own right and equips the reader with a broader perspective than traditional signal processing textbooks.

How Goodhart's Law Can Save Machine Learning Research


"When a measure becomes a target, it ceases to be a good measure." Stochastic Gradient Descent (SGD) has been responsible for many of the most outstanding achievements in machine learning. The objective of SGD is to optimise a target in the form of a loss function. But SGD fails in finding'standard' loss functions in a few settings as it converges to the'easy' solutions. As we see above, when classifying sheep, the network learns to use the green background to identify the sheep present.

The Roadmap of Mathematics for Deep Learning


Knowing the mathematics behind machine learning algorithms is a superpower. If you have ever built a model for a real-life problem, you probably experienced that being familiar with the details can go a long way if you want to move beyond baseline performance. This is especially true when you want to push the boundaries of state of the art. However, most of this knowledge is hidden behind layers of advanced mathematics. Understanding methods like stochastic gradient descent might seem difficult since it is built on top of multivariable calculus and probability theory.



The motive behind Creating this repo is to feel the fear of mathematics and do what ever you want to do in Machine Learning, Deep Learning and other fields of AI . So, try this Code in your python notebook which is provided in edx Course. In this Repo you will also learn the Libraries which are essential like numpy, pandas, matplotlib... I am going to upload new material when i find those material useful, you can also help me in keeping this repo fresh. Selecting the right algorithm which includes giving considerations to accuracy, training time, model complexity, number of parameters and number of features.

Machine Learning & Linear Algebra


Linear algebra is essential in Machine Learning (ML) and Deep Learning (DL). It is not hard. You just need to bring yourself up to speed. I will skip fundamentals like what is a vector, and matrix…

Linear Algebra 101 -- Part 1


I believe understanding fundamental concepts is crucial when it comes to learning something advanced. Because the fundamentals are the basis where you build your advanced knowledge on top of. If you put more things on top of the weak basis, it could break apart in the end, meaning you end up not fully understanding any of the materials you learned. Then you might need to go back again to learn the fundamentals before going back to learn the most exciting advanced materials which could be time consuming. Linear Algebra is one of the fundamental topics that you should be very comfortable with.

How to code Logistic Regression from scratch with NumPy


Let's first think of the underlying math that we want to use. In the above equations, X is the input matrix that contains observations on the row axis and features on the column axis; y is a column vector that contains the classification labels (0 or 1); f is the sum of squared errors loss function; h is the loss function for the MLE method. So, this is our goal: translate the above equations into code. We plan to use an object-oriented approach for implementation. We'll create a LogisticRegression class with 3 public methods: fit(), predict(), and accuracy().

Linear Algebra 101 -- Part 9: Singular Value Decomposition (SVD)


Singular Value Decomposition (SVD) is another type of decomposition. Unlike eigendecomposition where the matrix you want to decompose has to be a square matrix, SVD allows you to decompose a rectangular matrix (a matrix that has different numbers of rows and columns). This is often more useful in a real-life scenario since the rectangular matrix could represent a wide variety of data that's not a square matrix. First, let's look at the definition itself. As you can see, SVD decomposes the matrix into 3 different matrices.

A Perspective on Theoretical Computer Science in Latin America

Communications of the ACM

Theoretical computer science is everywhere, for TCS is concerned with the foundations of computing and computing is everywhere! In the last three decades, a vibrant Latin American TCS community has emerged: here, we describe and celebrate some of its many noteworthy achievements. Computer science became a distinct academic discipline in the 1950s and early 1960s. The first CS department in the U.S. was formed in 1962, and by the 1970s virtually every university in the U.S. had one. In contrast, by the late 1970s, just a handful of Latin American universities were actively conducting research in the area. Several CS departments were eventually established during the late 1980s. Often, theoreticians played a decisive role in the foundation of these departments. One key catalyst in articulating collaborations among the few but growing number of enthusiastic theoreticians who were active in the international academic arena was the foundation of regional conferences.