# Recent questions tagged neural-network

1
A neuron with $3$ inputs has the weight vector $\begin{bmatrix} 0.2 & -0.1 & 0.1 \end{bmatrix}^{T}$ and a bias $\theta =0.$ If the input vector is $X=\begin{bmatrix} 0.2 & 0.4 & 0.2 \end{bmatrix}^{T}$ then the total input to the neuron is: $0.20$ $1.0$ $0.02$ $-1.0$
2
Which of the following is an example of unsupervised neural network? Back-propagation network Hebb network Associative memory network Self-organizing feature map
3
ln neural network, the network capacity is defined as: The traffic (tarry capacity of the network The total number of nodes in the network The number of patterns that can be stored and recalled in a network None of the above
4
Which of the following can be an application of neural network ? Sales forecasting Data validation Risk management All of the above
1 vote
5
A perceptron has input weights W1 = -3.9 and W2 = 1.1 with threshold value T = 0.3. What output does it give for the input x1 = 1.3 and x2 = 2.2? (A) -2.65 (B) -2.30 (B) 0 (D) 1
6
An example of a data mining algorithm which uses squared error score function is : CART algorithm back propagation algorithm a priori algorithm vector space algorithm
1 vote
7
Let R and S be two fuzzy relations defined as and Then, the resulting relation, $T$, which relates elements of universe of $X$ to elements of universe of $Z$ using max-product composition is given by
8
What are the following sequence of steps taken in designing a fuzzy logic machine ? Fuzzification $\rightarrow$ Rule evaluation $\rightarrow$ Defuzzification Fuzzification $\rightarrow$ Defuzzification $\rightarrow$ Rule evaluation Rule evaluation $\rightarrow$ Fuzzification $\rightarrow$ Defuzzification Rule evaluation $\rightarrow$ Defuzzification $\rightarrow$ Fuzzification
9
Consider the following statements about a perception : $I$. Feature detector can be any function of the input parameters. $II$. Learning procedure only adjusts the connection weights to the output layer. Identify the correct statement out of the following : $I$ is false and $II$ is false. $I$ is true and $II$ is false. $​I$ is false and $II$ is true. $I$ is true and $II$ is true.
10
Suppose the function y and a fuzzy integer number around - 4 for x are given as $y=(x-3)^2 + 2$. Around - 4 ={(2, 0.3), (3, 0.6), (4, 1), (5, 0.6), (6, 0.3)} respectively. Then f(Around-4) is given by {(2, 0.6), (3, 0.3), (6, 1), (11, 0.3)} {(2, 0.6), (3, 1), (6, 1), (11, 0.3)} {(2, 0.6), (3, 1), (6, 0.6), (11, 0.3)} {(2, 0.6), (3, 0.3), (6, 0.6), (11, 0.3)}
11
Let A and B be two fuzzy integers defined as: A={(1.0.3), (2, 0.6), (3, 1), (4, 0.7), (5, 0.2)} B={(10, 0.5), (11, 1), (12, 0.5)} Using fuzzy arithmetic operation given by $\mu_{A+B^{(Z)}} = \underset{x+y=z}{\oplus} (\mu_A (x) \otimes \mu_B(y))$ $f(A+B)$ ... 15, 1), (16, 0.5), (17, 0.2)} {(11, 0.3), (12, 0.5), (13, 0.6), (14, 1), (15, 0.7), (16, 0.5), (17, 0.2)}
12
Consider the two class classification task that consists of the following points: Class $C_1$ : [1 1.5] [1 -1.5] Class $C_2$ : [-2 2.5] [-2 -2.5] The decision boundary between the two classes using single perceptron is given by: $x_1+x_2+1.5=0$ $x_1+x_2-1.5=0$ $x_1+1.5=0$ $x_1-1.5=0$
13
In a single perceptron, the updation rule of weight vector is given by $w(n+1) = w(n) + \eta [d(n)-y(n)]$ $w(n+1) = w(n) - \eta [d(n)-y(n)]$ $w(n+1) = w(n) + \eta [d(n)-y(n)]*x(n)$ $w(n+1) = w(n) - \eta [d(n)-y(n)]*x(n)$
1 vote
14
Support of a fuzzy set $A= \big\{ \frac{x_1}{0.2}, \frac{x_2}{0.15}, \frac{x_3}{0.9}, \frac{x_4}{0.95}, \frac{x_5}{0.15} \big \}$ ... $\{x_3, x_4 \}$ $\{x_1, x_2, x_3, x_4, x_5\}$
15
Let A be a set of comfortable houses given as $A = \big\{ \frac{x_1}{0.8}, \frac{x_2}{0.9}, \frac{x_3}{0.1}, \frac{x_4}{0.7} \big \}$ and be the set of affordable houses $B = \big\{ \frac{x_1}{0.9}, \frac{x_2}{0.8}, \frac{x_3}{0.6}, \frac{x_4}{0.2} \big \}$ Then the set of ... $\big\{ \frac{x_1}{0.7}, \frac{x_2}{0.7}, \frac{x_3}{0.7}, \frac{x_4}{0.9} \big \}$
1 vote
16
Consider a single perception with weights as given in the following figure: and $f(t)$ is defined as $f(t) \bigg\{ 1, t>0 \: 0, t \leq 0$ The above perception can solve OR problem AND problem XOR problem All of the above
1 vote
17
If A and B are two fuzzy sets with membership functions $\mu _A (x)=\{0.6,0.5,0.1,0.7,0.8\}$ $\mu_B(x)=\{0.9, 0.2, 0.6, 0.8, 0.5\}$ Then the value of $\mu_{\overline{A \cup B} }(x)$ will be $\{0.9, 0.5, 0.6, 0.8, 0.8\}$ $\{0.6, 0.2, 0.1, 0.7, 0.5 \}$ $\{0.1, 0.5, 0.4, 0.2, 0.2\}$ $\{0.1, 0.5, 0.4, 0.2, 0.3 \}$
A fuzzy set A on R is ______ iff $A(\lambda x_1 + (1- \lambda)x_2) \geq min [A(x_1), A(x_2)]$ for all $x_1, x_2 \in R$ and all $\lambda \in [0,1]$ where minimum denotes the minimum operator. Support $\alpha$ - cut Convex Concave