You've learned how a neuron calculates its weighted sum and how an activation function transforms that result. Now, let's put it all together to see how a neuron produces its final output.
Engagement Message
Ready to practice the full two-step process?
Type
Fill In The Blanks
Markdown With Blanks
A neuron receives an input of 4, with a weight of 0.5 and a bias of -3. It uses the ReLU activation function. What is the final output?
Fill in the blanks to solve it:
Weighted Sum = (
4*0.5) + (-3) = [[blank:-1]] Final Output = ReLU(-1) = [[blank:0]]
Suggested Answers
- -1
- 0
Type
Multiple Choice
Practice Question
Which of these values could be an output from a neuron using a Sigmoid activation function?
A. 1.5 B. -0.7 C. 0.85 D. 10
Suggested Answers
- A
- B
- C - Correct
- D
Type
Swipe Left or Right
Practice Question
Let's practice identifying activation function outputs. Swipe each value to the function that's most likely to have produced it.
Labels
- Left Label: ReLU
- Right Label: Tanh
Left Label Items
- 12.5
- 5
- 100
Right Label Items
- -0.9
- 0.5
- -1
Type
Multiple Choice
Practice Question
A neuron's weighted sum calculation results in -5. Which activation function would produce an output of 0?
A. Sigmoid B. ReLU C. Tanh D. None of the above
Suggested Answers
- A
- B - Correct
- C
- D
Type
Sort Into Boxes
Practice Question
Sort these concepts into the correct part of a neuron's process.
Labels
- First Box Label: Weighted Sum
- Second Box Label: Activation
First Box Items
- Inputs
- Weights
- Bias
Second Box Items
- ReLU
- Sigmoid
- Non-linearity
Type
Fill In The Blanks
Markdown With Blanks
Fill in the blanks to describe the roles of different activation functions.
For a binary classification problem where the output must be between 0 and 1, the [[blank:Sigmoid]] function works well. For cases where we want negative inputs to become zero, [[blank:ReLU]] can be used.
Suggested Answers
- ReLU
- Sigmoid
- Tanh
