A subset of Machine learning
Uses Neural networks. The word deep comes from having more than 2 hidden layers in them. this means that ==deep learning models can automatically extract features from raw data without Feature Engineering.==
traditional machine learning techniques might be efficient for linear separations or simpler patterns, deep learning excels at handling vast amounts of unstructured data like images and natural language and descovering intricate structures between them.
It contains wideley used neural network architectures:
- Foundation Models
- LSTM, RNN, CNN
Deep learning algorithms are essentially blackbox models, while we can describe their architectures and components and essentially understand the optimization of the weight parameters, we do not know what their respective neurons are measuring.