Conventional machine learning methods tend to succumb to environmental changes whereas deep learning adapts to these changes by constant feedback and improving the model. Deep learning is facilitated by neural networks which mimic the neurons in the human brain and embed multiple-layer architecture (few visible and few hidden)
The transfer learning approach is being used by most deep learning. It's a process which involves fine-tuning a pre-trained model.
In order to train a deep learning network from scratch, you’d need to capture a very large labeled dataset apart from designing a network architecture which will learn the features and mimic.
It’s a more specialized, slightly less common approach to deep learning where the network is used as a feature extractor.