Feature extraction – representation of unstructured data in a structured way

On: May 31, 2019

In: AI, Algorithms, Computer Vision, Deep Machine Learning, NLP, Reinforcement Learning

Images – A table of pixels, usually of RGB(3D columns – a.k.a a tensor) – can be ravled/unrolled/flattened to a 1D longer array.

Sound – long series of numbers(1D array) when digitally recorded(x = time(duration column), y = amplitude of the sound) – usually represented by frequences.

Text – parts of speech, embeddings, word frequency.

Previous Post: Reduce and Expand in Down/Up Sampling without Aliasing

Next Post: R Sqaured for Regression Evaluation

Comments are closed, but trackbacks and pingbacks are open.