- Create model building odds before they come out. Explains to user how the odds are created and gives an explanation of things to consider.
- Allows user to make an “optimal” bet.
- Has user take a survey to predict what bet they should make even if they believe lakers win they can say what they value about the lakers ie passing and then make the economic bet not the emotional one
- Host model, machine learning model build, infrastructure, deployment, stats knowdlege, think of this as creating multifaceted project (putting everything together) and software skills and data ML skills and create mvp and have ability to test iterate
( full model, have scraper that scrapes live to update the model, host model, create front end).
Know more sports interesting good networking bro culture networking surface --> hulu live ? youtube tv?
- Neural networks (aka artificial neural networks or neural nets) are a class of machine learning models which are inpsired by the structure and function of the biological neural networks like the human brain. Neural networks are often useful for image recognition, natural language processing, and time series prediction (data which is ordered chronologically wherein the predicition variable is something in the future).
1. Neurons and activation functions
- A neural network consists of interconnected computational units called neurons or nodes.
- Each neuron takes one or more input values, applies a transformation, and produces an output.
- The transormation is usually performed using an activation function which introduces non-linearity into the model.
- Without activation function, outputs would solely be linear relationships and the neural network would not be able to pick up on complex patterns.
- Activation functions are mathematical functions applied to the output of an individual neuron in a neural network.
- the purpose of an activation function is to determine whether or not a neuron should be activated or "fired" based on the weighted sum of its inputs
- without activation functions neural networks would simply be a series of linear operations and the ability to pick up on complex patterns would be quite limited.
commonly used activation functions:
- Sigmoid Function (Logistic Function):
- Formula: f(x) = 1 / (1 + exp(-x))
- Range: (0, 1)
- S-shaped curve, mapping any real-valued number to a value between 0 and 1.
- It is often used in the output layer for binary classification problems or when the output needs to be interpreted as probabilities.