Author: Packt Publishing<\/p>\n
Deep learning<\/a>, an emerging branch of machine learning, has garnered a lot of recognition in the field of technology over the last decade. It is regarded as a game-changer in AI, with distinct progress in computer vision, natural language processing (NLP), speech and other areas of machine learning. This year an Indeed survey found \u2018deep learning engineer\u2019 to be the best job in a tech position<\/a> in the USA.<\/span><\/p>\n<\/p>\n Though deep learning has many benefits and a very appealing track record, not everybody can afford deep learning. It has some downsides like large data requirements, being excessively expensive, and has a high computing time. Below is a breakdown of Rachael Tatman\u2019s talk \u201cPut down the deep learning: When not to use neural networks and what to do instead<\/a>\u201d at the PyCon 2019<\/a> conference that delved into the problems with deep learning. Tatman is a data science advocate at Kaggle.<\/span><\/p>\n<\/p>\n Deep learning models require a very large amount of data in order to perform better than other techniques. Also, according to Tatman, just the compute of a simple image generation model in deep learning can cost around $60,000. This cost will increase with the complexity of the data models. It additionally requires expensive GPUs and hundreds of machines which will again deepen the cost to the user. Many less skilled people also find it difficult to adopt deep learning, as there is no standard theory available for learning about deep learning tools. The choice of a deep learning tool depends on the user\u2019s knowledge of topology, training method, and other parameters. Next, deep learning also takes a lot of time for training large models.<\/span><\/p>\n<\/p>\n As the talk progresses, Tatman provides a list of three different types of models that can be used instead of deep learning. The three proposed models are regression-based models, tree-based models and distance-based models. Let\u2019s have a brief look at each of them below:<\/span><\/p>\n<\/p>\n The biggest advantage of a regression-based model is that it has a \u201cwell-principled\u201d understanding of problems and provides many kinds of regression models, unlike deep learning. Users can simply work through the flowchart and decide on the best type of regression model for their data.<\/span><\/p>\n<\/p>\n Some other advantages of regression models include its \u201cfast to fit\u201d feature. This means that it is much faster to fit when compared to a neural network, especially \u201cif you’re working with a well-optimized library the Python regression libraries tend to vary wildly so you might want to do a little bit of shopping around\u201d.<\/em> It also works well with small data as Tatman affirmed that she has worked on eight dozen data points. She added that since regression models are easy to interpret, she was able to learn many useful and interesting things from the data.<\/span><\/p>\n A few drawbacks of regression models are that a bit more data preparation is needed than for some other methods. They also require validation as regression models are based on strong assumptions about the distribution of the data points or the distribution of the errors.<\/span><\/p>\n<\/p>\n Tatman also proclaimed that if she were to use a single machine learning model for the rest of her life, it would be a mixed-effects regression model. Mixed-effects models are extensions of linear regression models for data which are collected and summarized in groups. It is mainly used to determine the expected or mean values of the subject population. She believes, \u201cyou need to do a little bit more hands-on stuff, you need to do your validation, you probably need to do some additional data cleaning,\u201d<\/em> however, it only takes some time to do a lot of computing in less money and data.<\/span><\/p>\n \u00a0<\/span><\/p>\nThe most interpretable: Regression-based models<\/span><\/h2>\n