Fundamentals of Machine Learning and Deep Learning

Fundamentals of Machine Learning and Deep Learning

What Is Machine Learning?

Machine learning is a subfield within artificial intelligence that deals with computer algorithms that can improve themselves via training data without explicit programming. It’s widely considered the most promising path for achieving true human-like artificial intelligence. 

Machine-learning algorithms can be broadly classified into three categories:

  • Supervised learning: You provide labels and present example inputs with their desired outputs and allow the algorithm to learn the rules that map inputs to outputs.  
  • Unsupervised learning: You don’t provide any labels, so the algorithm is allowed to find its own structure for processing inputs (e.g., discovering hidden patterns in data).
  • Reinforcement learning: The algorithm repeatedly interacts with a dynamic environment with a specific goal, such as winning a game or driving a car. The algorithm approximates the optimal solution to the problem through repeated trial and error.

In this article, we’ll give a brief overview of machine learning and deep learning, and the differences between the two concepts.

What Is Deep Learning?

Deep learning is a branch of machine learning that uses artificial neural networks to approximate human-like intelligence. Inspired by human neurons, deep learning uses graph theory to arrange weighting algorithms into layers of nodes and edges. Deep-learning algorithms are great at processing unstructured data such as images or language. 

Technically, to be classified as “deep,” a neural network must contain hidden layers between the input and output layers of a perceptron—the base structure of a neural network. These layers are considered “hidden” because they have no connection to the outside world. Examples of deep-learning architectures include:

  • Feed-forward (FF): Data passes in one direction from the input layer through the hidden layers and out the output layer—all nodes are connected and data never cycles back through the hidden layers. FF is used in data compression and basic image processing. 
  • Recurrent neural networks (RNN): A type of FF network that adds a time delay to the hidden layers which allows access to previous information during a current iteration. This feedback loop approximates memory and makes RNNs great for language processing.  A good example of this is predictive text which relies on the words you use most often to tailor its suggestions. 
  • Convolutional neural networks (CNN): A convolution is a mathematical operation on two functions that produces a third function describing how one is modified by the other. Used primarily for image recognition and classification, CNNs are the “eyes” of AI. The hidden layers in a CNN act as mathematical filters using weighted sums to identify edges, color, contrast, and other elements of a pixel.

Test Drive FlashBlade

Experience a self-service instance of Pure1® to manage Pure FlashBlade™, the industry's most advanced solution delivering native scale-out file and object storage.

Machine Learning vs Deep Learning

Deep learning is considered a subset of machine learning. The main differentiator that distinguishes deep-learning algorithms from other machine-learning algorithms is the use of artificial neural networks. And the main feature that makes a neural network “deep” is the presence of hidden layers between the input and output layers that make up a basic perceptron.

Benefits of Deep Learning

Deep-learning algorithms are great at processing unstructured data, provided you have the processing power to do so. This gives deep learning an advantage over other machine-learning algorithms when it comes to unsupervised and reinforcement learning. Recent advances in AI owe a lot to the increase in the viability of deep-learning neural networks thanks to improvements in processing power and data storage.

How Pure Storage Powers Machine-learning Apps

Pure Storage® is uniquely positioned to both leverage and support the world of AI. Deep-learning neural networks require data that is both big and fast. Pure’s all-flash storage solutions combine the performance of 100% NVMe flash memory with AI-powered predictive analytics to deliver a Modern Data Experience™. With Pure, you can:

  • Consolidate your data-storage silos into a unified data hub
  • Accelerate time to insights with real-time/log analytics
  • Experience the future of AI-driven data-storage management with Pure1 Meta®
  • Power your AI solutions with AIRI®, a full-stack, AI-ready infrastructure solution from Pure Storage and NVIDIA
  • Get full-stack support for AI and machine-learning lifecycles with FlashStack®, a converged infrastructure solution developed in partnership with Cisco.
800-379-7873 +44 20 3870 2633 +43 720882474 +32 (0) 7 84 80 560 +33 9 75 18 86 78 +49 89 12089 253 +353 1 485 4307 +39 02 9475 9422 +31 (0) 20 201 49 65 +46-101 38 93 22 +45 2856 6610 +47 2195 4481 +351 210 006 108 +966112118066 +27 87551 7857 +34 51 889 8963 +41 31 52 80 624 +90 850 390 21 64 +971 4 5513176 +7 916 716 7308 +65 3158 0960 +603 2298 7123 +66 (0) 2624 0641 +84 43267 3630 +62 21235 84628 +852 3750 7835 +82 2 6001-3330 +886 2 8729 2111 +61 1800 983 289 +64 21 536 736 +55 11 2655-7370 +52 55 9171-1375 +56 2 2368-4581 +57 1 383-2387