We look at different approaches when it comes to training a system. For example, taking this project in hand, we need to train the system to recognize the different types of punches thrown.

Neural Network

Neural networks are a set of algorithms, modeled loosely after the human brain, that are designed to recognize patterns. Neural networks are being applied to many real-life problems today, including speech and image recognition, spam email filtering, finance, and medical diagnosis, to name a few.

3 reasons to study neural computation:

• To understand how the brain actually works: it's very large and very complicated and made from things that die when you poke it, so we need to use computer simulations.
• To grasp a neuron-inspired model of parallel computation and their adaptive connections: it is a very different style from sequential computation.
• To solve practical problems by using novel learning algorithms inspired by the brain: learning algorithms can be very useful even if they are not how the brain actually works.

For Pro-Box, we need a program coded up in python, using tensorflow backend and keras.

With these tools, we can train the model to recognize the type of punches.

1. Jab
2. hook
3. Uppercut