The various approaches for building algorithms are :
- First of all, there are deterministic algorithms that are very transparent and predictable, but it may be very difficult to build a custom algorithm for complex tasks, which will work in all cases.
- Next, there's the machine learning technique, where we train the model based on features we get from data. We don't need a lot of data to train models in a reliable way, but we need to make a separate process for training validation and testing.
- Finally, there's the deep learning approach, where we train our own neural networks. The main advantage of this is that we can use raw data without predefined features. The downside is that we need a lot of data and ...