Collaborating Authors


#011 Linear Algebra - Nonlinear Least Squares - Master Data Science 11.07.2021


Most of the time the equation of the model involves higher-order and higher-degree functions. In this post, we will learn how to solve the harder nonlinear equations using a heuristic algorithm of finding the least-squares approximate solution. Practically, almost all problems can be represented as a set of nonlinear equations. However, solving them is a little more complex than the method we used to apply for solving linear equations. Let us consider a set of \(m \) nonlinear equations and \(n \) variables.

Embeddings in Machine Learning: Everything You Need to Know


I like puppies and soulcycle. Embeddings have pervaded the data scientist's toolkit, and dramatically changed how NLP, computer vision, and recommender systems work. However, many data scientists find them archaic and confusing. Many more use them blindly without understanding what they are. In this article, we'll deep dive into what embeddings are, how they work, and how they are often operationalized in real-world systems. To understand embeddings, we must first understand the basic requirements of a machine learning model. Specifically, most machine learning algorithms can only take low-dimensional numerical data as inputs. In the neural network below each of the input features must be numeric. That means that in domains such as recommender systems, we must transform non-numeric variables (ex.

Linear Algebra Part-2


Unfortunately, no one can be told what the matrix is. You have to see yourself. In this blog, lets continue the topic from previous blog where we left off. Blog covers 3-D Linear transformations, determinants, Inverse Matrices, Column Space, Null Space, Non Square matrices as transformations between dimensions. Example: Consider a linear transformation with 3-Dimentional vectors as inputs and 3-Dimentional vectors as output.

Dynamic Time Warping explained using Python and HAR dataset


The Time series classification is a very common task where you will have data from various domains like Signal processing, IoT, human activity, and more and the ultimate aim is to train a specific model so that it can predict the class of any time series with almost perfect accuracy. The given dataset should have labeled time sequences so that our model can predict the class of the time series accurately. One Classic solution to this problem is by using the method of the K Nearest neighbor algorithm. Here in this article, we are going to skip over the usual approach of Euclidean distance and we will use the Dynamic Time Warping or DTW metric. This method does take into consideration that when we are comparing two different time series, they might vary in length and speed.

JPMorgan's guide to quantum machine learning in finance


We suggested in January that it might be a good idea to familiarize yourself with quantum computing if you want to maximize your future employability in financial services. A new academic paper from JPMorgan's Future Lab for Applied Research and Engineering helps explain why. Authored by Marco Pistoia, JPMorgan's head of quantum technology and head of research, plus members of his team, the paper stresses that quantum computing will impact financial services sooner than you think. Goldman Sachs and JPMorgan have both been building teams of quantum researchers and Goldman has already used quantum methods to speed up derivatives pricing by over a thousand times. The finance industry stands to benefit from quantum computing "even in the short term," says JPMorgan.

Implementing A Deep Learning Chess Engine From Scratch


The neural network is the intuitive and positional side of the hybrid algorithm. It is trained on thousands of master chess games. This game on the left is a game that is played between two neural networks. When looking at the moves that the engine play, it is very clear that the network has learnt some basic positional concepts. For example, you can see that the engines push knights to the center, fianchetto bishops,and push pawns to gain space.

Why you need math for programming


If you are a HTML code ninja you definitely will not require math in your work. But for most programmers math is inevitable. Without mathematical knowledge, you are basically handicapped. Here are a couple of math topics essential for programmers. It is one of the most important areas of mathematics and is often found in programming.

HAGEN: Homophily-Aware Graph Convolutional Recurrent Network for Crime Forecasting Artificial Intelligence

The crime forecasting is an important problem as it greatly contributes to urban safety. Typically, the goal of the problem is to predict different types of crimes for each geographical region (like a neighborhood or censor tract) in the near future. Since nearby regions usually have similar socioeconomic characteristics which indicate similar crime patterns, recent state-of-the-art solutions constructed a distance-based region graph and utilized Graph Neural Network (GNN) techniques for crime forecasting, because the GNN techniques could effectively exploit the latent relationships between neighboring region nodes in the graph. However, this distance-based pre-defined graph cannot fully capture crime correlation between regions that are far from each other but share similar crime patterns. Hence, to make an accurate crime prediction, the main challenge is to learn a better graph that reveals the dependencies between regions in crime occurrences and meanwhile captures the temporal patterns from historical crime records. To address these challenges, we propose an end-to-end graph convolutional recurrent network called HAGEN with several novel designs for crime prediction. Specifically, our framework could jointly capture the crime correlation between regions and the temporal crime dynamics by combining an adaptive region graph learning module with the Diffusion Convolution Gated Recurrent Unit (DCGRU). Based on the homophily assumption of GNN, we propose a homophily-aware constraint to regularize the optimization of the region graph so that neighboring region nodes on the learned graph share similar crime patterns, thus fitting the mechanism of diffusion convolution. It also incorporates crime embedding to model the interdependencies between regions and crime categories. Empirical experiments and comprehensive analysis on two real-world datasets showcase the effectiveness of HAGEN.

Tomato Disease Classification with CNN Architecture


The aim of this project is to identify various diseases on tomatoes based on their leaves. It is very important in agriculture to identify diseases immediately. To detect the problem in real-time, we develop a Deep Learning model that can be installed on embedded devices and can be used in greenhouses, or by adding the model to some apps people can manually upload a photo of tomato leaves and check how healthy it is. Our model is able to find healthy tomatoes and 9 different diseases. The public dataset, which is available on Kaggle has been used to train and test the model.

Multi-View Video-Based 3D Hand Pose Estimation Artificial Intelligence

Hand pose estimation (HPE) can be used for a variety of human-computer interaction applications such as gesture-based control for physical or virtual/augmented reality devices. Recent works have shown that videos or multi-view images carry rich information regarding the hand, allowing for the development of more robust HPE systems. In this paper, we present the Multi-View Video-Based 3D Hand (MuViHand) dataset, consisting of multi-view videos of the hand along with ground-truth 3D pose labels. Our dataset includes more than 402,000 synthetic hand images available in 4,560 videos. The videos have been simultaneously captured from six different angles with complex backgrounds and random levels of dynamic lighting. The data has been captured from 10 distinct animated subjects using 12 cameras in a semi-circle topology where six tracking cameras only focus on the hand and the other six fixed cameras capture the entire body. Next, we implement MuViHandNet, a neural pipeline consisting of image encoders for obtaining visual embeddings of the hand, recurrent learners to learn both temporal and angular sequential information, and graph networks with U-Net architectures to estimate the final 3D pose information. We perform extensive experiments and show the challenging nature of this new dataset as well as the effectiveness of our proposed method. Ablation studies show the added value of each component in MuViHandNet, as well as the benefit of having temporal and sequential information in the dataset.