Nothing substantial. Deep Learning just stresses that the feedforward neural network does have many hidden layers, that’s all.

Deep learning don't need feature extraction before training because the method can do it automatic (feature extraction not separated from the training process with the algorithm) . Machine learning must pass the feature extraction before training.

DL is a subset of ML, DL generally uses huge quantities of unlabeled data while ML uses smaller quantities of labeled data (and thus requires a shorter learning period). DL is a neural net with more than three layers. For these reasons DL is generally preferred while modeling phenomena with k variables and unpredictable outcomes (i.e non linear phenomena).

ML is used for making predictions in tasks such as classification and regression while DL is used to explore unknown datasets to find hidden patterns mainly through clustering, dimensionality reduction and association.

The choice between ML and DL depends on the type and quantity of your data, your knoweldge of the data and the aim of your study.

I agree with the previous answers.

Machine learning refers to a set of algorithms and techniques that enable computers to learn from data and make predictions or decisions without being explicitly programmed. In other words, machine learning algorithms learn patterns in data and use those patterns to make predictions or decisions. Machine learning can be supervised, unsupervised, or semi-supervised, depending on the type of data and the learning task.

Deep learning is a subset of machine learning that is based on artificial neural networks, which are designed to mimic the structure and function of the human brain. Deep learning algorithms can learn from large amounts of data and can automatically extract features from the data without human intervention. Deep learning models can be used for a wide range of tasks, such as image recognition, natural language processing, speech recognition, and autonomous driving.

Here are some key differences between machine learning and deep learning:

1. Complexity: Deep learning algorithms are more complex and require more computational resources than traditional machine learning algorithms.

2. Feature extraction: In traditional machine learning, feature extraction is done manually by domain experts, while in deep learning, feature extraction is done automatically by the neural network.

3. Data requirements: Deep learning algorithms require more data than traditional machine learning algorithms to achieve high accuracy.