**Mini-Batch Gradient Descent(MBGD)**:

- **Pros**:
  - It's good at a large dataset while **BGD** is not.
  - It's good at online learning while **BGD** is not. *Online learning is the way which a model incrementally learns from a stream of dataset in real-time.
  - It doesn't need the repreparation of a whole dataset if you want to update a model while **BGD** needs.
  - It can more easily escape local minima or saddle points than **BGD**.
- **Cons**:
  - The computation is less stable than **BGD**.
  - It's less strong in noise(noisy data) than **BGD**.
  - It gets a less accurate value than **BGD**.