{"slug": "tensors-explained-part-2-why-tensors-are-useful", "title": "Tensors Explained Part 2: Why Tensors Are Useful", "summary": "Tensors enable hardware acceleration by leveraging GPUs and TPUs to perform parallel mathematical operations efficiently, making them essential for training neural networks. They also support automatic differentiation, which simplifies backpropagation by automatically calculating derivatives and applying the chain rule. This allows tensors to handle complex mathematical computations behind the scenes as neural networks grow in complexity.", "body_md": "In the [previous article](https://dev.to/rijultp/tensors-explained-part-1-how-ai-systems-represent-data-mbj), we started with a brief introduction to **tensors**.\n\nIn this article, we will explore **why tensors are useful**.\n\nUnlike normal scalars, arrays, matrices, and multi-dimensional matrices, tensors are designed to take advantage of **hardware acceleration**.\n\nTensors do not just store data in different shapes.\n\nThey are also designed to perform mathematical operations on that data **efficiently and quickly**.\n\nTensors can take advantage of **GPUs (Graphics Processing Units)**, which many of us use in our day-to-day devices.\n\nGPUs are very good at performing many mathematical calculations in parallel, making them useful for training neural networks.\n\nThere is also specialized hardware called **TPUs (Tensor Processing Units)**.\n\nTPUs are specifically designed to work with tensors and help neural networks run even faster.\n\nAnother important use case of tensors is in **backpropagation**.\n\nIn neural networks, we estimate the optimal weights and biases using backpropagation.\n\nThis process requires calculating many derivatives and applying the **chain rule**.\n\nInstead of manually calculating all these derivatives, tensor frameworks can handle this automatically using something called **automatic differentiation**.\n\nThis means that even as neural networks become more complex, tensors help manage the difficult mathematical calculations behind the scenes.\n\nSo that is it for tensors.\n\nIn the next article, we will explore another topic\n\nAI agents write code fast. They also silently remove logic, change behavior, and introduce bugs -- without telling you. You often find out in production.\n\n[git-lrc](https://github.com/HexmosTech/git-lrc) fixes this. It hooks into git commit and reviews every diff before it lands. 60-second setup. Completely free.\n\nAny feedback or contributors are welcome! It's online, source-available, and ready for anyone to use.\n\nGive it a ⭐ [star on Github](https://github.com/HexmosTech/git-lrc)", "url": "https://wpnews.pro/news/tensors-explained-part-2-why-tensors-are-useful", "canonical_source": "https://dev.to/rijultp/tensors-explained-part-2-why-tensors-are-useful-31g1", "published_at": "2026-05-29 03:52:37+00:00", "updated_at": "2026-05-29 04:11:51.883939+00:00", "lang": "en", "topics": ["neural-networks", "machine-learning", "artificial-intelligence", "ai-chips", "ai-infrastructure"], "entities": ["GPU", "TPU"], "alternates": {"html": "https://wpnews.pro/news/tensors-explained-part-2-why-tensors-are-useful", "markdown": "https://wpnews.pro/news/tensors-explained-part-2-why-tensors-are-useful.md", "text": "https://wpnews.pro/news/tensors-explained-part-2-why-tensors-are-useful.txt", "jsonld": "https://wpnews.pro/news/tensors-explained-part-2-why-tensors-are-useful.jsonld"}}