Implement the perceptron rule training of the network using f(net) = sgn (net), c = 1, and the following data specifying the initial weights w', and the two training pairs W¹ = 1 X₁ = [ 2 1 , d₁= -1, X₂= El d₂= 1, Repeat the training sequence (X₁, di), (X2, d2) until two correct responses in a row are achieved. List the net values obtained during training. (use a binary activation function), fast

Is it conceivable for the following network to be effective and productive? Do not generalize; rather, provide an instance.

Implement Algorithm (highest label preflow push algorithm). Let N = (G,c,s,t) be a flow network, where G is a symmetric digraph given by incidence lists Av. Moreover, let Q be a priority queue with priority function d, and rel a Boolean variable.

Consider a dataset of N = 3 x 105 nodes and L = 2 × 105 links. Assuming that the data is well described by a random graph model would you expect to find a giant component in the network? Select one: O a. Yes O b. No

I need to implement a python code for Q learning and SARSA method. My example involves a cliff walking experiment where the rewards are -1 except for the region marked as cliff if the agent steps there the reward is -100 and the agent is sent back to the start. The values used are alpha = 0.1, y or gamma = 1 and the e- greedy action is 0.1. After using these values on both algorithm the results needs to be shown by using matplot. The graph should have episodes in the x axis and sum of rewards during episode on the y axis. It needs to be smoothed out by averaging over 10 runs and, plotting moving average over last 10 episodes. This needs to be done in python using numpy and panda but I'm not allowed to use gym library or any other library.

Write a program in Scilab that samples f (x )=3e^−x sinx at x=0,1,2,3,4,5 and then, on the same graph, plots nearest-neighbor, linear and spline interpolations of these data using the interp1 function. The interpolation plots should have 200 samples uniformly spaced over 0≤x≤5 .

Consider eight points on the Cartesian two-dimensional x-y plane. a g C For each pair of vertices u and v, the weight of edge uv is the Euclidean (Pythagorean) distance between those two points. For example, dist(a, h) : V4? + 1? = /17 and dist(a, b) = v2? + 0² = 2. Because many pairs of points have identical distances (e.g. dist(h, c) V5), the above diagram has more than one minimum-weight spanning tree. dist(h, b) = dist(h, f) Determine the total number of minimum-weight spanning trees that exist in the above diagram. Clearly justify your answer.

Suppose we are fitting a neural network with three hidden layers to a training set. It is found that the cross validation error Jcv(0) is much larger than the training error Jtrain (0). Should we increase the number of hidden layers?

A unigram is a sequence of words of length one (i.e. a single word).• A bigram is a sequence of words of length two.• The conditional probability of an event E2 given another event E1, written p(E2|E1), is the probability that E2 will occur given that event E1 has already occurred.We write p(w(k)|w(k-1)) for the conditional probability of a word w in position k, w(k), given the immediately preceding word, w(k-1). You determine the conditional probabilities by determining unigram counts (the number of times each word appears, written c(w(k)), bigram counts (the number of times each pair of words appears, written c(w(k-1) w(k)), and then dividing each bigram count by the unigram count of the first word in the bigram:p(WORD(k)|WORD(k-1)) = c(WORD(k-1) WORD(k)) / c(WORD(k-1)) Apply and incorporate instrutions to code below. #include <stdio.h>//including headers#include <string.h>#include <stdlib.h> struct node{//structure intialization int data; struct node *next; };…

Consider the following perceptron with the activation function f(I)=arctan(I-0.6). Use delta learning rule toupdate the weights w1 and w2 for the training data x=[1, 1] and D=1. (Choose k=0.2)   it wont let me post the screenshot of the model but the w1 is 0.2 and w2 is 0.4