Tensor
A multi-dimensional array of numbers — the fundamental data structure in deep learning. Scalars are 0D tensors, vectors are 1D, matrices are 2D, and higher-dimensional arrays are nD tensors.
Why It Matters
Tensors are the building blocks of neural network computation. Every input, weight, and output in a model is represented as a tensor.
Example
An image represented as a 3D tensor with dimensions [height=224, width=224, channels=3 (RGB)], or a batch of 32 such images as a 4D tensor [32, 224, 224, 3].
Think of it like...
Like a spreadsheet that can have more than 2 dimensions — a regular spreadsheet is 2D (rows and columns), but tensors can extend into 3D, 4D, and beyond.
Related Terms
Neural Network
A computing system inspired by the biological neural networks in the human brain. It consists of interconnected nodes (neurons) organized in layers that process information and learn to recognize patterns.
TPU
Tensor Processing Unit — Google's custom-designed chip specifically optimized for machine learning workloads. TPUs are designed for matrix operations that are fundamental to neural network computation.
Deep Learning
A specialized subset of machine learning that uses artificial neural networks with multiple layers (hence 'deep') to learn complex patterns in data. Deep learning excels at tasks like image recognition, speech processing, and natural language understanding.