One of the measures of the health of a deep learning project is the degree to which it utilizes the training resources that it was allocated. Whether you are training in the cloud or on your own private infrastructure, training resources cost money, and any block of time in which they are left idle represents a potential opportunity to increase training throughput and overall productivity. This is particularly true for the training accelerator -- typically the most expensive training resource -- whether it be a GPU, a Google TPU, or a Habana Gaudi. This blog is a sequel to a previous post on the topic of Overcoming Data Preprocessing Bottlenecks in which we addressed the undesired scenario in which your training accelerator, henceforth assumed to be a GPU, finds itself idle while it waits for data input from an overly tasked CPU. The post covered several different ways of addressing this type of bottleneck and demonstrated them on a toy example, all the while emphasizing that the best option would very much depend on the specifics of the model and project at hand.

In this course, you'll be learning various supervised ML algorithms and prediction tasks applied to different data. You'll learn when to use which model and why, and how to improve the model performances. We will cover models such as linear and logistic regression, KNN, Decision trees and ensembling methods such as Random Forest and Boosting, kernel methods such as SVM. Prior coding or scripting knowledge is required. We will be utilizing Python extensively throughout the course.

So far, to showcase BigML's upcoming Object Detection release, we have demonstrated how you can annotate images on the platform, we have covered an example use case to detect cats and dogs and shared how to execute the newly available features by using the BigML Dashboard, as well as another example to build a plant disease detector. In contrast, this installment demonstrates how to perform Object Detection by calling the BigML REST API. Briefly, Object Detection is a supervised learning technique for images that not only shows where an object is in the image, but it also can show where instances of objects from multiple classes are located in the image. Let's jump in and see how we can put it to use programmatically. Before using the API, you must set up your environment variables.

Inductive logic programming (ILP) is a form of machine learning. The goal of ILP is to induce a hypothesis (a set of logical rules) that generalises training examples. As ILP turns 30, we provide a new introduction to the field. We introduce the necessary logical notation and the main learning settings; describe the building blocks of an ILP system; compare several systems on several dimensions; describe four systems (Aleph, TILDE, ASPAL, and Metagol); highlight key application areas; and, finally, summarise current limitations and directions for future research.

Simply put, training data is a dataset that is used to train a machine learning model. The purpose of training data is to provide the model with examples of how it should behave in different situations. Without training data, it would be very difficult for machines to learn how to perform specific tasks. In this article, we will discuss why training data is important for AI and computer vision, and we will provide some tips on where you can find high-quality training datasets. Training data is important for AI and computer vision because it allows machines to learn from examples.

Often, artificial intelligence (AI) is used broadly to describe all types of systems that seem to make decisions we do not quite understand. But while many reasonably complex systems make decisions like this, it does not immediately make them "intelligent." For example, I might not understand how my "smart" oven thermometer seems to know when my roast beef will be perfectly done, or how my garden light knows when to turn on, but the engineers putting together the (not-too-complex) mathematical equation do. There are many other systems that, at first glance, look intelligent--but they are just constructed by smart people. We should not label these as "intelligent" because that suggests they are making their own decisions instead of simply following a human-designed path. A better way to distinguish (artificially) intelligent systems from those that just follow human-made rules is to look for the person who can explain the systems' inner workings (i.e., the person ultimately responsible for what the systems do).

In this hands-on tutorial, we will provide you with a reimplementation of SimCLR self-supervised learning method for pretraining robust feature extractors. This method is fairly general and can be applied to any vision dataset, as well as different downstream tasks. In a previous tutorial, I wrote a bit of a background on the self-supervised learning arena. Time to get into your first project by running SimCLR on a small dataset with 100K unlabelled images called STL10. Code is available on Github.

Generative pretraining for sequence modeling has emerged as a unifying paradigm for machine learning in a number of domains and modalities, notably in language and vision (Radford et al., 2018; Chen et al., 2020; Brown et al., 2020; Lu et al., 2022). Recently, such a pretraining paradigm has been extended to offline reinforcement learning (RL) (Chen et al., 2021; Janner et al., 2021), wherein an agent is trained to autoregressively maximize the likelihood of trajectories in the offline dataset. During training, this paradigm essentially converts offline RL to a supervised learning problem (Schmidhuber, 2019; Srivastava et al., 2019; Emmons et al., 2021). However, these works present an incomplete picture as policies learned via offline RL are limited by the quality of the training dataset and need to be finetuned to the task of interest via online interactions. It remains an open question whether such supervised learning paradigm can be extended to online settings. Unlike language and perception, online finetuning for RL is fundamentally different from the pretraining phase as it involves data acquisition via exploration. The need for exploration renders traditional supervised learning objectives (e.g., mean squared error) for offline RL insufficient in the online setting. Moreover, it has been observed that for standard online algorithms, access to offline data can often have zero or even negative effect on the online performance (Nair et al., 2020). Hence, the overall pipeline for offline pretraining followed by online finetuning for RL policies needs a careful consideration of training objectives and protocols.

Often, artificial intelligence (AI) is used broadly to describe all types of systems that seem to make decisions we do not quite understand. But while many reasonably complex systems make decisions like this, it does not immediately make them "intelligent." For example, I might not understand how my "smart" oven thermometer seems to know when my roast beef will be perfectly done, or how my garden light knows when to turn on, but the engineers putting together the (not-too-complex) mathematical equation do. There are many other systems that, at first glance, look intelligent--but they are just constructed by smart people. We should not label these as "intelligent" because that suggests they are making their own decisions instead of simply following a human-designed path. A better way to distinguish (artificially) intelligent systems from those that just follow human-made rules is to look for the person who can explain the systems' inner workings (i.e., the person ultimately responsible for what the systems do).

This tutorial is an extension of Method Of Lagrange Multipliers: The Theory Behind Support Vector Machines (Part 1: The Separable Case)) and explains the non-separable case. In real life problems positive and negative training examples may not be completely separable by a linear decision boundary. This tutorial explains how a soft margin can be built that tolerates a certain amount of errors. In this tutorial, we'll cover the basics of a linear SVM. We won't go into details of non-linear SVMs derived using the kernel trick.