What are neural networks?
A neural network isa machine learning algorithm that receives as input a number of variables or features, and finds the best combination of those features to predict an output.
What are the 4 main ways a neural network can learn?
Supervised
Learning:
a category of machine learning that uses labeled datasets to train algorithms to predict outcomes and recognise patterns.
Unsupervised & Self-supervised
Learning:
machine learning models that identify structure in unlabeled data.
Transfer Learning:
involves taking features learned in one problem, and exploiting them in a similar new problem. For example, the characteristics of a model that has learned to identify raccoons may be useful in starting a model to identify tanukis.
Reinforcement Learning:
is a type of machine learning that does not require a dataset to learn from. It can learn from the experience it gathers.
