We provide an in-depth introduction to Random Forest, with an explanation to how it works, its advantages and disadvantages, important hyperparameters and a full example Python implementation.
What linear regression is and how it can be implemented for both two variables and multiple variables using Scikit-Learn, which is one of the most popular machine learning libraries for Python.
Adversarially Constrained Autoencoder Interpolation (ACAI; Berthelot et al., 2018) is a regularization procedure that uses an adversarial strategy to create high-quality interpolations of the learned representations in autoencoders.
A brief overview of a new method for explainable AI (XAI), called anchors, introduce its open-source implementation and show how to use it to explain models predicting the survival of Titanic passengers.
This article presents an infographic for choosing which chart type is most useful in a given scenario. The infographic and chart types are then explored for greater clarity.
We outline our four-step model to categorize how successfully a company uses analytics by its ability to show the analytics, uncover underlying trends, and take action based on them.
Object Detection in Aerial Images is a challenging and interesting problem. By using Keras to train a RetinaNet model for object detection in aerial images, we can use it to extract valuable information.
Introducing Black Box AI, a system for automated decision making often based on machine learning over big data, which maps a user’s features into a class predicting the behavioural traits of the individuals.
This article demonstrates creating similar plots in R and Python using two of the most prominent data visualization packages on the market, namely ggplot2 and Seaborn.
This tutorial discusses how to use the genetic algorithm (GA) for reducing the feature vector extracted from the Fruits360 dataset in Python mainly using NumPy and Sklearn.
Data science is said to change the manufacturing industry dramatically. Let's take under consideration several data science use cases in manufacturing that have already become common and brought benefits to the manufacturers.
We explain deep compression for improved inference efficiency, mobile applications, and regularization as technology cozies up to the physical limits of Moore's law.
This post shows how to train an LSTM Model using Keras and Google CoLaboratory with TPUs to exponentially reduce training time compared to a GPU on your local machine.
With huge and growing popularity of Microsoft Azure, getting that certification will advance your career. Consider these 8 reasons for taking an Azure certification course
In this blog, I’ll walk you through a personal project in which I cheaply built a classifier to detect anti-semitic tweets, with no public dataset available, by combining weak supervision and transfer learning.
We present some of our favorite breakthroughs in Machine Learning and AI in recent times, complete with papers, video links and brief summaries for each.
The Executive Guide covers the benefits to your business, the build-or-buy process, and gives a practical overview for implementing ML in your organization.
The basic idea looks simple: find the gist, cut off all opinions and detail, and write a couple of perfect sentences, the task inevitably ended up in toil and turmoil. Here is a short overview of traditional approaches that have beaten a path to advanced deep learning techniques.
In this article you will learn about Luminoth, an open source computer vision library which sits atop Sonnet and TensorFlow and provides object detection for images and video.
An analysis of the current state of the competition between US, Europe, and China in AI, examining research, patent publications, global datasphere, devices and IoT, people, and more.
We investigate what a typical data scientist looks like and see how this differs from this time last year, looking at skill set, programming languages, industry of employment, country of employment, and more.
In this article, I’ll share a few ways in which we, as data scientists, can use the power of the Pareto Principle to guide our day-to-day activities.
We investigate how to use a custom loss function to identify fair odds, including a detailed example using machine learning to bet on the results of a darts match and how this can assist you in beating the bookmaker.
For the 2019 international women's day, we profile a new set of 19 inspiring women who lead the field in AI, Big Data, Data Science, and Machine Learning fields.
Ethical algorithm design is becoming a hot topic as machine learning becomes more widespread. But how do you make an algorithm ethical? Here are 5 suggestions to consider.
Today we’re looking at a more general fake news problem: detecting fake news that is being spread on a social network. This is a summary of a recent paper which demonstrates why we should also look at the social context: the publishers and the users spreading the information!
Here's a third set of 10 free books for machine learning and data science. Have a look to see if something catches your eye, and don't forget to check the previous installments for reading material while you're here.
In this post, the author shows how BERT can mimic a Bag-of-Words model. The visualization tool from Part 1 is extended to probe deeper into the mind of BERT, to expose the neurons that give BERT its shape-shifting superpowers.
In this tutorial, you will get a brief understanding of what Neural Networks are and how they have been developed. In the end, you will gain a brief intuition as to how the network learns.
Self-Attention Generative Adversarial Networks (SAGAN;Â Zhang et al., 2018) are convolutional neural networks that use the self-attention paradigm to capture long-range spatial relationships in existing images to better synthesize new images.
ODSC East 2019 has multiple tracks for both Data Scientists and Data Engineers, including workshops, talks, and training sessions. Save 45% with code KDN45.
OpenAI recently released a very large language model called GPT-2. Controversially, they decided not to release the data or the parameters of their biggest model, citing concerns about potential abuse. Read this researcher's take on the issue.
MobileNets are a family of mobile-first computer vision models for TensorFlow, designed to effectively maximize accuracy while being mindful of the restricted resources for an on-device or embedded application.