Register

Recent questions and answers in Artificial Intelligence

1.2k
views
1 answers
0 votes
GATE DS&AI 2024 | Question: 13
Let $h_{1}$ and $h_{2}$ be two admissible heuristics used in $A^{*}$ search.Which ONE of the following expressions is always an admissible heuristic?$h_{1}+h_{2}$h_{1} ... 1} / h_{2},\left(h_{2} \neq 0\right)$\left|h_{1}-h_{2}\right|$
User Avatar
248
views
0 answers
0 votes
Memory Based GATE DA 2024 | Question: 32
Consider two admissible heuristic functions, \(h_1\) and \(h_2\). Determine which of the following combinations are admissible:\(\frac{h_1}{h_2}\) \(\left(h_2 > 0\right)\) \\\(h_1 ... {h}_2\) \\\(\left| h_1 - h_2 \right|\) \\\(h_1 + h_2\)
User Avatar
203
views
0 answers
0 votes
Memory Based GATE DA 2024 | Question: 50
You are provided with three images, each depicting a different face of a six-sided dice. Based on these images, determine the correct option.
User Avatar
360
views
2 answers
0 votes
UPENN | ML | Cross validation
Suppose you have picked the parameter \( \theta \) for a model using 10-fold cross-validation. The best way to pick a final model to use and estimate its error ... the \( \theta \) you found; use the average CV error as its error estimate
User Avatar
725
views
2 answers
2 votes
DRDO CSE 2022 Paper 2 | Question: 31
What is the State $\mathrm{X}$ called for the following machine learning model?
User Avatar
589
views
1 answers
0 votes
DA Practice | UPENN | ML | Naive Bais
Suppose you have a three-class problem where class label \( y \in \{0, 1, 2\} \), and each training example \( \mathbf{X} \) has 3 binary attributes \( X_1, ... an example using the Naive Bayes classifier?(a) 5b) 9(c) 11(d) 13(e) 23
User Avatar
361
views
1 answers
0 votes
UPENN | ML Questions for GATE DA
In fitting some data using radial basis functions with kernel width $σ$, we compute training error of $345$ and a testing error of $390$.(a) increasing ... error(C) not enough information is provided to determine how $σ$ should be changed
User Avatar
364
views
1 answers
0 votes
UPENN | ML | DA Practice | Regularization
After applying a regularization penalty in linear regression, you find that some of the coefficients of $w$ are zeroed out. Which of the following penalties might have been used?(a) ... (c) L2 norm(d) either (A) or (B)(e) any of the above
User Avatar
469
views
1 answers
0 votes
AI Sample Question for DS-AI
Imagine you are guiding a robot through a grid-based maze using the A* algorithm. The robot is currently at node A (start) and wants to reach node B (goal). ... A* calculation? A) Node CB) Node DC) Node ED) Not enough information to decide
User Avatar
324
views
1 answers
0 votes
UPENN | DS-AI Sample | Decision Tree
When choosing one feature from \(X_1, \ldots, X_n\) while building a Decision Tree, which of the following criteria is the most appropriate to maximize? (Here, \(H()\) means entropy, and \(P( ... X_j)\)(d) \(H(Y | X_j)\)(e) \(H(Y) - P(Y)\)
User Avatar
373
views
1 answers
0 votes
UPENN | ML | DECISION TREE
Given the following table of observations, calculate the information gain $IG(Y |X)$ that would result from learning the value of $X$. XYRedTrueGreenFalseBrownFalseBrownFalse (a) 1/2(b) 1(c) 3/2(d) 2(e) none of the above
User Avatar
351
views
1 answers
0 votes
Decision Tree | Sample Question
$True$ or $False?$ If decision trees such as the ones we built in class are allowed to have decision nodes based on questions that can have many ... tend to add the multiple answer questions to the tree before adding the binary questions
User Avatar
296
views
1 answers
0 votes
UPENN | ML | Cross Validation
P1: In the limit of infinite training and test data, consistent estimators always give at least as low a test error as biased estimators. P2: Leave-one out cross ... ?Only P1 is TrueOnly P2 is TrueP1 is True and P2 is FalseBoth are False
User Avatar
182
views
0 answers
0 votes
UPENN | ML | DA Practice
Using the same data as above \( \mathbf{X} = [-3, 5, 4] \) and \( \mathbf{Y} = [-10, 20, 20] \), assuming a ridge penalty \( \lambda = 50 \), what ratio versus the MLE ... \mathbf{w}}_{\text{ridge}} \) will be?(a)] 2b)] 1(c)] 0.666(d)] 0.5
User Avatar
217
views
1 answers
0 votes
UPENN | ML | DA Practice
Consider the statements:$P1:$ It is generally more important to use consistent estimators when one has smaller numbers of training examples.$P2:$ It is generally more important to ... C) Only $P2$ is True(D) Both $P1$ and $P2$ are False
User Avatar
266
views
1 answers
0 votes
DA Practice | UPENN | ML | Bias-Variance Trade Off | Regularization
Suppose we have a regularized linear regression model: \[ \text{argmin}_{\mathbf{w}} \left||\mathbf{Y} - \mathbf{Xw} \right||^2 + k \|\ ... bias, increases variance(d)] Decreases bias, decreases variance(e)] Not enough information to tell
User Avatar
179
views
1 answers
0 votes
UPENN | ML | DA Practice | Bias-Variance Trade-Off
Suppose we have a regularized linear regression model: \[ \text{argmin}_{\mathbf{w}} \left||\mathbf{Y} - \mathbf{Xw} \right||^2 + \lambda \ ... , increases variance(d)] Decreases bias, decreases variance(e)] Not enough information to tell
User Avatar
223
views
1 answers
0 votes
UPENN | Midterm | K Fold Validation | DA Practice |
Suppose we want to compute $10-Fold$ Cross-Validation error on $100$ training examples. We need to compute error $N1$ times, and the Cross-Validation error is the average of the errors. ... $N1 = 10, N2 = 100, N3 = 10$
User Avatar
2.8k
views
3 answers
3 votes
ISRO2018-75
ln neural network, the network capacity is defined as:The traffic (tarry capacity of the networkThe total number of nodes in the networkThe number of patterns that can be stored and recalled in a networkNone of the above
User Avatar
1.5k
views
2 answers
0 votes
UGC NET CSE | October 2020 | Part 2 | Question: 36
Which of the following is NOT true in problem solving in artificial intelligence?Implements heuristic search techniqueSolution steps are not explicitKnowledge is impreciseIt works on or implements repetition mechanism
User Avatar
4.5k
views
2 answers
1 votes
UGC NET CSE | June 2012 | Part 3 | Question: 21
$A^*$ algorithm uses $f'=g+h'$ to estimate the cost of getting from the initial state to the goal state, where $g$ is a measure of cost getting from initial state to ... $g=0$h'=0$h'=1$
User Avatar
5.3k
views
2 answers
3 votes
UGC NET CSE | June 2012 | Part 3 | Question: 2
In Delta Rule for error minimizationweights are adjusted w.r.to change in the outputweights are adjusted w.r.to difference between desired output and actual ... are adjusted w.r.to difference between output and outputnone of the above
User Avatar
13.3k
views
2 answers
0 votes
UGC NET CSE | December 2012 | Part 2 | Question: 46
Back propagation is a learning technique that adjusts weights in the neutral network by propagating weight changes.Forward from source to sinkBackward from sink to sourceForward from source to hidden nodesBackward from sink to hidden nodes
User Avatar
5.8k
views
2 answers
3 votes
UGC NET CSE | December 2015 | Part 3 | Question: 8
Forward chaining systems are ____ where as backward chaining systems are ____Data driven, Data drivenGoal driven, Data drivenData driven, Goal drivenGoal driven, Goal driven
User Avatar
2.6k
views
2 answers
1 votes
UGC NET CSE | December 2015 | Part 3 | Question: 45
Reasoning strategies used in expert systems includeForward chaining, backward chaining and problem reductionForward chaining, backward chaining and boundary ... and back propagationForward chaining, problem reduction and boundary mutation
User Avatar
1.9k
views
2 answers
3 votes
UGC NET CSE | December 2015 | Part 3 | Question: 46
Language model used in LISP isFunctional programmingLogic programmingObject oriented programmingAll of the above
User Avatar
573
views
1 answers
0 votes
Artificial Intelligence Heuristic problem Confusion
User Avatar
2.2k
views
2 answers
0 votes
UGC NET CSE | July 2018 | Part 2 | Question: 73
In heuristic search algorithms in Artificial Intelligence (AI), if a collection of admissible heuristics $h_1 \dots h_m$ is available for a problem and none of them dominates any of the ... h_m(n)\}$h(n)=sum\{h_1(n), \dots , h_m(n)\}$
User Avatar
1.7k
views
2 answers
0 votes
UGC NET CSE | July 2018 | Part 2 | Question: 78
Consider the following two sentences:The planning graph data structure can be used to give a better heuristic for a planning problemDropping negative effects from every ... but sentence b is falseSentence a is false but sentence b is true
User Avatar
6.7k
views
2 answers
1 votes
UGC NET CSE | June 2019 | Part 2 | Question: 97
Consider the following:EvolutionSelectionReproductionMutationWhich of the following are found in genetic algorithms?b, c and d onlyb and d onlya, b, c and da, b and d only
User Avatar
1.6k
views
4 answers
0 votes
UGC NET CSE | June 2016 | Part 3 | Question: 66
A perceptron has input weights $W_1=-3.9$ and $W_2=1.1$ with threshold value $T=0.3.$ What output does it give for the input $x_1=1.3$ and $x_2=2.2?$-2.65$-2.30$0$1$
User Avatar
2.7k
views
4 answers
0 votes
UGC NET CSE | July 2018 | Part 2 | Question: 74
Consider following sentences regarding $A^*$, an informed search strategy in Artificial Intelligence (AI).$A^*$ expands all nodes with $f(n)<C^*$ ... statements b and statement c are trueAll the statements a, b and c are true
User Avatar
466
views
1 answers
1 votes
Machine Learning
You are a designing a machine learning model for a binary classification problem. The model has three features: f1, f2, f3. Derive the objective and loss function for this problem.
User Avatar
315
views
1 answers
0 votes
Machine Learning Self-doubt
Please Solve this question with full explanation.
User Avatar
439
views
1 answers
0 votes
Ai Questions | DS-AI Paper | GATE 2024
Given a tree with a branching factor of 3 and a depth of 4, calculate the maximum number of nodes expanded during a breadth-first search.
User Avatar
650
views
1 answers
1 votes
DRDO CSE 2022 Paper 2 | Question: 28 (a)
Provide the correct answer for the following:________ is not the best evaluation metric for cancer prediction problem.
User Avatar
422
views
0 answers
0 votes
GATE DS-AI questions | ML
Consider the feature transform z = [L0(x) L1(x) L2(x)]T with Legendre polynomials and the linear model h(x) = w T .z. For the regularized hypothesis with w = [−1 ... 1] T , what is h(x) explicitly as a function of x? write solution for It.
User Avatar
553
views
1 answers
1 votes
DRDO CSE 2022 Paper 2 | Question: 28 (b)
Provide the correct answer for the following:The phenomena in which training error of the model decreases but test error increases is called___________.
User Avatar
434
views
1 answers
1 votes
DRDO CSE 2022 Paper 2 | Question: 32
A perceptron consists of weights $\left[w_{1}, w_{2}, w_{3}, w_{4}\right]=[0.5,2,1,-3]$. The activation function is provided as $y=f(z)=1$ if $z \geq 2$ otherwise $0,$ ...
User Avatar
To see more, click for all the questions in this category.