1Question 1A Deep Neural Network is shown in Figure 1. The aim of this network is to classify human and dog.1. Calculate the initial error of the Deep Neural Network by feeding the following input: X₁ = 5, X₂ = 2.The X₁ indicates the length of the tail and X₂ indicates the number of eyes.2. Update the layer 2 weights (ws,we, w7,ws) of the Deep Neural Network shown in Figure 1 for a singleiteration. The learning rate is set to a = 1 and there are no biases in the neurons.3. Recalculate the error with the updated weights of layer 2 and report its improvement with respect tothe initial error (percentage wise).4. (Bonus Question) Update and report the layer 1 weights (w₁,w₂,3,W4) of the network and estimatethe improvement to the error.InputX₁=5W₁-0w₂ = 0W₁-0Layer 13₁₂0Layer 2ysyPredictedOutputRealOutput10BEFigure 1: A Deep Neural Network designed for dog or human detection Formula SheetThe ANN neurons function is described as below:ny = o(w₁ X₁ + bi)where w, b, X and o(2) are the weight, bias, input and activation function respectively. Sigmoid function(2) = 1 is widely used as an activation function (outputs 0-1).The error function can also be shown as the following:3E1Əw(L)EΙΣni=1(3-9₁)²y(L) = 6 (2(1))The parital derivative of error, with respect of the weight for layer (L) is calculated as below:- = y(L-1)ø′ (z(L)) 2 (y(L) — ŷ),where the derivative of the sigmoid activation function is o' (2)) = ó (z(²)) ((1 – ó (z(¹))).For each iteration, the weight can then be updated by the following:JEow'where learning rate a dictates how fast the weights need to be adjusted.(1)ww-a(2)(3)(4)(5)

Since you have asked a question with multiple sub-parts, we will solve the first three sub-parts for…

1 Question 1 A Deep Neural Network is shown in Figure 1. The aim of this network is to classify human and dog. 1. Calculate the initial error of the Deep Neural Network by feeding the following input: X₁ = 5, X₂ = 2. The X₁ indicates the length of the tail and X₂ indicates the number of eyes. 2. Update the layer 2 weights (ws,we,w7,ws) of the Deep Neural Network shown in Figure 1 for a single iteration. The learning rate is set to a = 1 and there are no biases in the neurons. 3. Recalculate the error with the updated weights of layer 2 and report its improvement with respect to the initial error (percentage wise). 4. (Bonus Question) Update and report the layer 1 weights (w₁,w₂,w₁,w₁) of the network and estimate the improvement to the error. Input X₁=5 X₂-2 ₂-0 Layer 1 3/₂ /₂0 Layer 2 Predicted Output Real Output 1 0 H BE Figure 1: A Deep Neural Network designed for dog or human detection

1 Question 1 A Deep Neural Network is shown in Figure 1. The aim of this network is to classify human and dog. 1. Calculate the initial error of the Deep Neural Network by feeding the following input: X₁ = 5, X₂ = 2. The X₁ indicates the length of the tail and X₂ indicates the number of eyes. 2. Update the layer 2 weights (ws,we,w7,ws) of the Deep Neural Network shown in Figure 1 for a single iteration. The learning rate is set to a = 1 and there are no biases in the neurons. 3. Recalculate the error with the updated weights of layer 2 and report its improvement with respect to the initial error (percentage wise). 4. (Bonus Question) Update and report the layer 1 weights (w₁,w₂,w₁,w₁) of the network and estimate the improvement to the error. Input X₁=5 X₂-2 ₂-0 Layer 1 3/₂ /₂0 Layer 2 Predicted Output Real Output 1 0 H BE Figure 1: A Deep Neural Network designed for dog or human detection

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Similar questions

PART D and E only PLEASE!
A Convolutional Neural Network (CNN) has 3 consecutive 5x5 convolutional layers with a stride of 1 without pooling. What is the size of the receptive field for a neuron (the set of input image pixels which activate the neuron) in the 3rd convolutional layer?
Why in neural networks synchronous updates can lead to infinite loops and not allow to retrieve the final pattern, but asynchronous updates cant?
Fill in the fields with the relevant information.All of the operations of addition, subtraction, multiplication, and division could be done using Leibniz's idea.
How does the forward and backward propagation through time in recurrent neural networks occurs/works?
Consider the following neural network. In order to have some numbers to work with, here are the initial weights, the biases, and training inputs/outputs. The goal is to optimize the weights so that the neural network can learn how to correctly map arbitrary inputs to outputs.
Which one to choose?
Convolutional Neural Networks In 1 convolution layer we have 7 filters of 3x3x3 applied to input volume 62x62x3 with stride 1 and pad 1. What is the size of the output volume? Give details of how you calculate the size of the output volume.
Artificial neural networks (ANNs) are computational models that are inspired by the structure and function of biological neural networks. ANNs consist of interconnected nodes that process and transmit information. There are various types of ANNs, including feedforward neural networks, recurrent neural networks, convolutional neural networks, and deep neural networks. Each type of ANN has a unique architecture and learning algorithm that enables it to perform specific tasks.
From a purely mathematical perspective, how would you describe supervised learning in neural networks?
A multi-layer neural network has its weight as below. All neurons use linear activation function. Calculate the MSE loss, for the input [2,1] that is correspond with the label [1,0]. ( 0.3 1 x1 O x2 Softmax y 1 x1 -0.2 x2 0.7 0.4 -0.5 -0.1 EO
guaranteed report to bartleby if post existing one