Some algorithms are quite easy to calculate, while others require complex steps and mathematics. The good news is that you usually do not have to compute an algorithm because there are a variety of languages like Python and R that make the process straightforward.<\/p>\n\n\n\n
As for machine learning, an algorithm is typically different from a traditional one. The reason is that the first step is to process data\u2014and then, the computer will start to learn.<\/p>\n\n\n\n
Even though there are hundreds of machine learning algorithms available, they can actually be divided into four major categories: supervised learning, unsupervised learning, reinforcement learning, and semi-supervised learning. We\u2019ll take a look at each.<\/p>\n\n\n\n
Supervised learning uses labeled data. For example, suppose we have a set of photos of thousands of dogs. The data is considered to be labeled if each photo identifies each for the breed. For the most part, this makes it easier to analyze since we can compare our results with the correct answer.<\/p>\n\n\n\n
One of the keys with supervised learning is that there should be large amounts of data. This helps to refine the model and produce more accurate results.<\/p>\n\n\n\n
But there is a big issue: The reality is that much of the data available is not labeled. In addition, it could be time consuming to provide labels if there is a massive dataset.<\/p>\n\n\n\n
Yet there are creative ways to deal with this, such as with crowdfunding. This is how the ImageNet system was built, which was a breakthrough in AI innovation. But it still took several years to create it.<\/p>\n\n\n\n
Or, in some cases, there can be automated approaches to label data. Take the example of\u00a0Facebook. In 2018, the company announced\u2014at its F8 developers conference\u2014it leveraged its enormous database of photos from Instagram, which were labeled with hashtags.12<\/sup><\/p>\n\n\n\n Granted, this approach had its flaws. A hashtag may give a nonvisual description of the photo\u2014say #tbt (which is \u201cthrowback Thursday)\u2014or could be too vague, like #party. This is why Facebook called its approach \u201cweakly supervised data.\u201d But the talented engineers at the company found some ways to improve the quality, such as by building a sophisticated hashtag prediction model.<\/p>\n\n\n\n All in all, things worked out quite well. Facebook\u2019s machine learning model , which included 3.5 billion photos, had an accuracy rate of 85.4%, which was based on the ImageNet recognition benchmark. It was actually the highest recorded in history, by 2%.<\/p>\n\n\n\n This AI project also required innovative approaches for building the infrastructure. According to the Facebook blog post:<\/p>\n\n\n\n Since a single machine would have taken more than a year to complete the model training, we created a way to distribute the task across up to 336 GPUs, shortening the total training time to just a few weeks. With ever-larger model sizes\u2014the biggest in this research is a ResNeXt 101-32x48d with over 861 million parameters\u2014such distributed training is increasingly essential. In addition, we designed a method for removing duplicates to ensure we don\u2019t accidentally train our models on images that we want to evaluate them on, a problem that plagues similar research in this area.13<\/a><\/sup><\/p>\n<\/blockquote>\n\n\n\n Going forward, Facebook sees potential in using its approach to various areas, including the following:<\/p>\n\n\n\n Unsupervised learning is when you are working with unlabeled data. This means that you will use deep learning algorithms to detect patterns.<\/p>\n\n\n\n By far, the most common approach for unsupervised learning is clustering, which takes unlabeled data and uses algorithms to put similar items into groups. The process usually starts with guesses, and then there are iterations of the calculations to get better results. At the heart of this is finding data items that are close together, which can be accomplished with a variety of quantitative methods:<\/p>\n\n\n\n In terms of use cases for clustering, one of the most common is customer segmentation, which is to help better target marketing messages. For the most part, a group that has similar characteristics is likely to share interests and preferences.<\/p>\n\n\n\n Another application is sentiment analysis, which is where you mine social media data and find the trends. For a fashion company, this can be crucial in understanding how to adapt the styles of the upcoming line of clothes.<\/p>\n\n\n\n Now there are other approaches than just clustering. Here\u2019s a look at three more:<\/p>\n\n\n\n\n
\n
Unsupervised Learning<\/h3>\n\n\n\n
\n
\n