You must be logged in to see worked solutions.

Already have an account? Log in here.

You must be logged in to see worked solutions.

Already have an account? Log in here.

In our computational model of a neuron, the inputs defined by the vector \(\vec{x}\) are “integrated” by taking the **bias** \(b\) plus the dot product of the **inputs** \(\vec{x}\) and **weights** \(\vec{w}.\) \[\vec{w} \cdot \vec{x} + b\] The dot product represents a "weighted sum" because it multiplies each input by a weight.

A biological interpretation is that the inputs defining \(\vec{x}\) are the outputs of other neurons, the weights defining \(\vec{w}\) are the strengths of the connections to those neurons, and the bias \(b\) impacts the threshold the computing neuron must surpass in order to fire.

You must be logged in to see worked solutions.

Already have an account? Log in here.

An activation function, \(H(v),\) is used to transform the integration (weighted sum) into a single output which determines whether or not the neuron would fire. For example, we might have \(H(v)\) as the Heaviside step function; that is, \[H(v) = \begin{cases} 1 & \mbox{if } v \ge 0, \\ 0 & \mbox{if } v \lt 0. \\ \end{cases}\]

Considering \(H(\vec{w} \cdot \vec{x} + b),\) how does *increasing* the bias \(b\) affect the likelihood of the neuron firing (all else equal), assuming that a 1 corresponds to firing?

You must be logged in to see worked solutions.

Already have an account? Log in here.

When \(H(v)\) is the Heaviside step function, the neuron modeled by \(H(\vec{w} \cdot \vec{x} + b)\) fires when \(\vec{w} \cdot \vec{x} + b\ge 0.\)

The hypersurface \(\vec{w} \cdot \vec{x} + b = 0\) is called the **decision boundary**, since it divides the input vector space into two parts based on whether the input would cause the neuron to fire. This model is known as a linear classifier because this boundary is based on a linear combination of the inputs.

The model above shows a decision boundary for predicting college admission based on the input \[\vec{x} = \begin{pmatrix}\text{SAT score} \\ \text{GPA} \end{pmatrix}\] and the activation function \(H(\vec{w} \cdot \vec{x} + b)\), where \(H(v)\) is the Heaviside step function. Which of the following is a possible value for the weight vector, \(\vec{w}?\)

You must be logged in to see worked solutions.

Already have an account? Log in here.

So far, we’ve considered an activation function \(H(v)\) with binary outputs, as inspired by a physical neuron. However, in ANNs, we don’t need to restrict ourselves to a binary function. Functions like the ones below avoid counterintuitive jumps and can model continuous values (e.g., a probability).

The power of ANNs is illustrated by the **universal approximation theorem**: ANNs using activation functions like these can model *any* continuous function, given some general requirements about the size and layout of the ANN.

You must be logged in to see worked solutions.

Already have an account? Log in here.

We’ve now built up a basic computational model of neurons. While one neuron might not seem powerful, connecting many together in a clever manner can yield a highly effective learning model. This turns out to be true for ANNs, as evidenced by the universal approximation theorem.

The remainder of this Exploration focuses on the methods used to construct and train ANNs, highlighting the intuition behind the models and their applications. **Let’s dive in!**

×

Problem Loading...

Note Loading...

Set Loading...