Optimization How to Use Maximum Likelihood Estimation for Parametric Classification Methods In some previous tutorials that discussed how Bayes' rule works, a decision was made based on some probabilities (e.g. the likelihood and prior). Either these probabilities were given explicitly

Data Science Introduction to Time Series Forecasting: Regression and LSTMs In the first part of this series, Introduction to Time Series Analysis, we covered the different properties of a time series, autocorrelation, partial autocorrelation, stationarity, tests for stationarity, and seasonality.

Data Science Introduction to Time Series Forecasting: Autoregressive Models & Smoothing Methods In Part 1 of this series we looked at time series analysis. We learned about the different properties of a time series, autocorrelation, partial autocorrelation, stationarity, tests for stationarity, and

Machine Learning Introduction to Time Series Analysis Time series analysis and forecasting have many applications: analyzing the sales of your retail chains, finding anomalies in the traffic you're getting to your servers, and predicting stock markets, to

Computer Vision Build A Flask Web App To Compress Images Using A Variational Autoencoder In this tutorial, we'll build a web application using Flask which will allow the user to upload images to be encoded (i.e., compressed) using a pre-trained variational autoencoder (VAE)

Machine Learning How to Apply Bayesian Decision Theory in Machine Learning In a previous article we discussed the theory behind Bayesian Decision Theory in detail. In this article we'll see how to apply Bayesian Decision Theory to different classification problems. We'll

Machine Learning Bayesian Decision Theory Explained Bayesian Decision Theory is the statistical approach to pattern classification. It leverages probability to make classifications, and measures the risk (i.e. cost) of assigning an input to a given

Keras How To Train Keras Models Using the Genetic Algorithm with PyGAD PyGAD is an open-source Python library for building the genetic algorithm and training machine learning algorithms. It offers a wide range of parameters to customize the genetic algorithm to work

Machine Learning Beginner's Guide to Boltzmann Machines in PyTorch As research progressed and researchers could bring in more evidence about the architecture of the human brain, connectionist machine learning models came into the spotlight. Connectionist models, which are also

Machine Learning Beginner's Guide to Quantum Machine Learning As a Data Scientist and Researcher, I always try to find answers to the problems I come across every day. Working on real-world problems, I have faced many complexities both

Computer Vision Object Detection Using Mask R-CNN with TensorFlow 2.0 and Keras In a previous tutorial, we saw how to use the open-source GitHub project Mask_RCNN with Keras and TensorFlow 1.14. In this tutorial, the project is inspected to replace

Computer Vision Faster R-CNN Explained for Object Detection Tasks This article gives a review of the Faster R-CNN model developed by a group of researchers at Microsoft. Faster R-CNN is a deep convolutional network used for object detection, that

Computer Vision How To Speed Up Object Detection Using NumPy Reshape and Transpose This is Part 4 of our ongoing series on NumPy optimization. In Parts 1 and 2 we covered the concepts of vectorization and broadcasting, and how they can be applied

Tools ML Platforms: Buy vs Build If you follow the emerging discipline of MLOps, by now you've probably heard of some of the well-known internally developed ML platforms like Uber's Michelangelo and AirBnB's BigHead. Â The big

Machine Learning Working with Different Genetic Algorithm Representations in Python Depending on the nature of the problem being optimized, the genetic algorithm (GA) supports two different gene representations: binary, and decimal. The binary GA has only two values for its

Machine Learning Building a Game-Playing Agent for CoinTex Using the Genetic Algorithm Games can have complex environments, where many different factors contribute to making a decision. An entire area of artificial intelligence is devoted to building game-playing agents that can make the

Machine Learning The 11 Best AI & Machine Learning Podcasts to Add to Your Listening Pipeline Add these podcasts to your weekly listening pipeline to learn from top thought leaders and developers about the future of ai and machine learning, as well as innovative use cases and products.

Machine Learning How To Implement Support Vector Machine With Scikit-Learn Support vector machine is one of the most popular classical machine learning methods. In this tutorial we'll cover SVM and its implementation in Python.

Gradient Gradient update (7/18/2018) GradientÂ° has been updated in response to a ton of feedback from the community. Here's a roundup of some of the things we've added recently.

Quilt Reproducible machine learning with PyTorch and Quilt In this article, we'll use Quilt to transfer versioned training data to a remote machine. We'll start with the Berkeley Segmentation Dataset, package the dataset, then train a PyTorch model for super-resolution imaging.

Tutorial Vectorization and Broadcasting with Pytorch Next time you're wondering why your machine learning code is running slowly, even on a GPU, consider vectorizing any loopy code!

GPU Machine Learning on Paperspace ML-In-Box: An effortless VM in the cloud, backed by a powerful GPU, and pre-loaded with all of the latest ML frameworks.