Exam (elaborations)
PHIL 3440 Exam 2 questions with correct answers
- Course
- Institution
PHIL 3440 Exam 2 questions with correct answers
[Show more]
Content preview
PHIL 3440 Exam 2 questions with correctanswers
What is an artificial neural network? - correct answer ✔✔A network of artificial neurons meant to mimic
the functioning of biological neural tissue.
What are the components of ANNs? - correct answer ✔✔An input layer and output layer composed of
"units" (artificial neurons), possibly hidden layers and convolutional layers (which look for specific
features), all of which are joined by weighted connections.
How do units compute their total input? - correct answer ✔✔The activation level of each connected unit
is multiplied by the weight of the connection, and then the sum of these weighted inputs is compared
against the unit's activation function.
How is the activation level of a unit determined? - correct answer ✔✔The weighted inputs of all
connected units are compared against an activation function.
Linear Activation Function - correct answer ✔✔Output varies linearly with total input.
Threshold Activation Function - correct answer ✔✔No output below a certain threshold, maximum
output above it.
Sigmoid Activation Function - correct answer ✔✔Asymptotic minimum and maximum output levels, and
linear activation between those two levels.
ReLU Activation Function - correct answer ✔✔Inactive up to a threshold, linear above it.
What is the simplest type of ANN? - correct answer ✔✔A perceptron; a single-layer neural network.
What is a boolean function? - correct answer ✔✔A function that returns either true or false.
, Which kinds of problems can be learned by a perceptron? - correct answer ✔✔Problems with solutions
that are linearly separable; simple boolean functions like OR, AND, NOT, and conditionals.
Serial vs Parallel Processing - correct answer ✔✔Serial: Many computations performed one after
another.
Parallel: Many computations at once.
Localist vs Distributed Representations - correct answer ✔✔Localist: Symbolic (one representation = one
or a few symbols), better for associating with other representations.
Distributed: Sub-symbolic (one representation is the conjunction of many units, each representing one
or fewer microfeatures), better for representing conjunctions of features.
Computational and Representational Features of Connectionist Networks - correct answer
✔✔Distributed representations, parallel computation, little distinction between information processing
and information storage, ability to "learn."
What influenced the development of connectionist networks? - correct answer ✔✔Inspired by biological
computation.
Advantages of Connectionist Networks - correct answer ✔✔Graceful Degradation (continue giving
correct or near-correct answers after damage) and Fault Tolerance (works with messy or incomplete
input data). Ability to learn. Parallel processing. Models biological cognition.
Which learning rule was designed for networks with hidden layers? - correct answer
✔✔Backpropagation algorithms.
Supervised vs Unsupervised Learning in ANNs - correct answer ✔✔Supervised involves known "correct"
output values for all training inputs, and an error signal is calculated to reduce the difference between
the actual output and the desired output.
Unsupervised involves the network essentially categorizing the data based on features that it determines
to be salient; no predetermined "correct" outputs.
The benefits of buying summaries with Stuvia:
Guaranteed quality through customer reviews
Stuvia customers have reviewed more than 700,000 summaries. This how you know that you are buying the best documents.
Quick and easy check-out
You can quickly pay through credit card or Stuvia-credit for the summaries. There is no membership needed.
Focus on what matters
Your fellow students write the study notes themselves, which is why the documents are always reliable and up-to-date. This ensures you quickly get to the core!
Frequently asked questions
What do I get when I buy this document?
You get a PDF, available immediately after your purchase. The purchased document is accessible anytime, anywhere and indefinitely through your profile.
Satisfaction guarantee: how does it work?
Our satisfaction guarantee ensures that you always find a study document that suits you well. You fill out a form, and our customer service team takes care of the rest.
Who am I buying these notes from?
Stuvia is a marketplace, so you are not buying this document from us, but from seller BravelRadon. Stuvia facilitates payment to the seller.
Will I be stuck with a subscription?
No, you only buy these notes for $13.99. You're not tied to anything after your purchase.
Can Stuvia be trusted?
4.6 stars on Google & Trustpilot (+1000 reviews)
62890 documents were sold in the last 30 days
Founded in 2010, the go-to place to buy study notes for 14 years now