日本欧洲视频一区_国模极品一区二区三区_国产熟女一区二区三区五月婷_亚洲AV成人精品日韩一区18p

代寫DTS101TC Introduction to Neural Networks Coursework

時間:2024-03-01  來源:  作者: 我要糾錯


Due: Sunday Apr.21th, 2024 @ 17:00

Weight: 100%

Overview

This coursework is the sole assessment for DTS101TC and aims to evaluate your compre-hension of the module. It consists of three sections: 'Short Answer Question', 'Image Classification Programming', and 'Real-world Application Question'. Each question must be answered as per the instructions provided in the assignment paper. The programming task necessitates the use of Python with PyTorch within a Jupyter Notebook environment, with all output cells saved alongside the code.

Learning Outcomes

A.   Develop an understanding of neural networks  –  their architectures, applications  and limitations.

B.   Demonstrate the ability to implement neural networks with a programming language

C.   Demonstrate the  ability to provide critical analysis on real-world problems and design suitable solutions based on neural networks.

Policy

Please save your assignment in a PDF document, and package your code as a ZIP file. If there are any errors in the program, include debugging information. Submit both the answer sheet and the ZIP code file via Learning Mall Core to the appropriate drop box. Electronic submission is the only method accepted; no hard copies will be accepted.

You must download your file and check that it is viewable after submission. Documents may become  corrupted  during  the  uploading  process  (e.g.  due  to  slow  internet  connections). However, students themselves are responsible for submitting a functional and correct file for assessments.

Avoid Plagiarism

.     Do NOT submit work from others.

.     Do NOT share code/work with others.

.     Do NOT copy and paste directly from sources without proper attribution.

.     Do NOT use paid services to complete assignments for you.

Q1. Short Answer Questions [40 marks]

The questions test general knowledge and understanding of central concepts in the course. The answers should be short. Any calculations need to be presented.

1.  (a.)  Explain the concept of linear separability. [2 marks]

(b.)  Consider the following data points from two categories: [3 marks]

X1  : (1, 1)    (2, 2)    (2, 0);

X2  : (0, 0)    (1, 0)    (0, 1).

Are they linearly separable? Make a sketch and explain your answer.

2.  Derive the gradient descent update rule for a target function represented as

od  = w0 + w1 x1 + ... + wnxn

Define the squared error function first, considering a provided set of training examples D, where each training example d ∈ D is associated with the target output td. [5 marks]

3.  (a.)  Draw a carefully labeled diagram of a 3-layer perceptron with 2 input nodes, 3 hidden nodes, 1 output node and bias nodes. [5 marks]

(b.)  Assuming that the activation functions are simple threshold, f(y) = sign(y), write down the input- output functional form of the overall network in terms of the input-to-hidden weights, wab , and the hidden-to-output weights, ˜(w)bc. [5 marks]

(c.)  How many distinct weights need to be trained in this network? [2 marks]

(d.)  Show that it is not possible to train this network with backpropagation. Explain what modification is necessary to allow backpropagation to work. [3 marks]

(e.)  After you modified the activation function, using the chain rule, calculate expressions for the fol- lowing derivatives

(i.) ∂J/∂y / (ii.) ∂J/∂˜(w)bc

where J is the squared error, and t is the target. [5 marks]

4.  (a.)  Sketch a simple recurrent network, with input x, output y, and recurrent state h. Give the update equations for a simple RNN unit in terms of x, y, and h. Assume it usestanh activation. [5 marks]

(b.)  Name one example that can be more naturally modeled with RNNs than with feedforward neural networks?  For a dataset X := (xt ,yt )1(k), show how information is propagated by drawing a feed-

forward neural network that corresponds to the RNN from the figure you sketch for k = 3.  Recall that a feedforward neural network does not contain nodes with a persistent state. [5 marks]

Q2. Image Classification Programming [40 marks]

For this  question,  you  will  build your  own image  dataset  and  implement a neural network  by Pytorch.   The question is split in a number of steps.  Every  step  gives you some marks.  Answer the  questions for  each step and include the screenshot of code  outputs  in your answer sheet.

- Language and Platform Python  (version  3.5  or  above)  with  Pytorch  (newest  version). You  may  use any libraries available on Python platform, such as numpy, scipy, matplotlib, etc.  You need to run the code in the jupyter notebook.

- Code Submission All of your dataset,  code  (Python files and ipynb files) should be  a package in a single ZIP file,  with  a PDF of your IPython  notebook with  output cells. INCLUDE your dataset in the zip file.

1. Dataset Build [10 marks]

Create an image dataset for classification with 120 images ( ‘.jpg’  format), featuring at least two cate- gories. Resize or crop the images to a uniform size of 128 × 128 pixels.  briefly describe the dataset you constructed.

2. Data Loading [10 marks]

Load your dataset, randomly split the set into training set (80 images), validation set (20 images) and test set (20 images).

For the training set, use python commands to display the number of data entries, the number of classes, the number of data entries for each classes, the shape of the image size.  Randomly plot 10 images in the training set with their corresponding labels.

3. Convolutional Network Model Build [5 marks]

//  pytorch .network

class  Network(nn.Module):

def  __init__ (self,  num_classes=?):

super(Network,  self).__init__ ()

self.conv1  =  nn.Conv2d(in_channels=3,  out_channels=5,  kernel_size=3,  padding=1) self.pool  =  nn.MaxPool2d(2,  2)

self.conv2  =  nn.Conv2d(in_channels=5,  out_channels=10,  kernel_size=3,  padding=1) self.fc1  =  nn.Linear(10  *  5  *  5,  100)

self.fc2  =  nn.Linear(100,  num_classes)

def  forward(self,  x):

x  =  self.pool(F.relu(self.conv1(x)))

x  =  self.pool(F.relu(self.conv2(x)))

x  =  x.view(-1,  10  *  5  *  5)

x  =  self.fc1(x)

x  =  self.fc2(x)

return  x

Implement Network, and complete the form below according to the provided Network. Utilize the symbol ‘-’ to represent sections that do not require completion. What is the difference between this model and AlexNet?

Layer

# Filters

Kernel Size

Stride

Padding

Size of

Feature Map

Activation Function

Input

Conv1


ReLU

MaxPool

Conv2


ReLU

FC1


-

-

-


ReLU

FC2


-

-

-

4. Training [10 marks]

Train the above Network at least 50 epochs. Explain what the lost function is, which optimizer do you use, and other training parameters, e.g., learning rate, epoch number etc.  Plot the training history, e.g., produce two graphs (one for training and validation losses, one for training and validation accuracy) that each contains 2 curves. Have the model converged?

5. Test [5 marks]

Test the trained model on the test set.  Show the accuracy and confusion matrix using python commands.

Q3. Real-world Application Questions [20 marks]

Give ONE specific  real-world problem  that  can  be  solved  by  neural networks.   Answer  the  questions  below (answer to  each  question should not  exceed 200 words) .

1.  Detail the issues raised by this real-world problem, and explain how neural networks maybe used to address these issues. [5 marks]

2.  Choose an established neural network to tackle the problem.  Specify the chosen network and indicate the paper in which this model was published. Why you choose it? Explain. [5 marks]

3.  How to collect your training data?  Do you need labeled data to train the network?  If your answer is yes, 請加QQ:99515681  郵箱:99515681@qq.com   WX:codehelp 

標簽:

掃一掃在手機打開當前頁
  • 上一篇:代做代寫COMPSCI 4091 Advanced Networked Systems
  • 下一篇:CSCI 2033代做、代寫Python, C++/Java編程
  • 無相關信息
    昆明生活資訊

    昆明圖文信息
    蝴蝶泉(4A)-大理旅游
    蝴蝶泉(4A)-大理旅游
    油炸竹蟲
    油炸竹蟲
    酸筍煮魚(雞)
    酸筍煮魚(雞)
    竹筒飯
    竹筒飯
    香茅草烤魚
    香茅草烤魚
    檸檬烤魚
    檸檬烤魚
    昆明西山國家級風景名勝區
    昆明西山國家級風景名勝區
    昆明旅游索道攻略
    昆明旅游索道攻略
  • NBA直播 短信驗證碼平臺 幣安官網下載 歐冠直播 WPS下載

    關于我們 | 打賞支持 | 廣告服務 | 聯系我們 | 網站地圖 | 免責聲明 | 幫助中心 | 友情鏈接 |

    Copyright © 2025 kmw.cc Inc. All Rights Reserved. 昆明網 版權所有
    ICP備06013414號-3 公安備 42010502001045

    日本欧洲视频一区_国模极品一区二区三区_国产熟女一区二区三区五月婷_亚洲AV成人精品日韩一区18p

              免费影视亚洲| 亚洲综合色丁香婷婷六月图片| 欧美巨乳在线观看| 小处雏高清一区二区三区 | 狠狠色狠狠色综合日日tαg| 欧美劲爆第一页| 久久久午夜精品| 亚洲欧美一区二区三区久久| 精品不卡一区| 国产精品手机视频| 国产精品电影在线观看| 欧美美女视频| 欧美大胆成人| 久久免费的精品国产v∧| 亚洲午夜日本在线观看| 亚洲欧洲在线看| 在线电影国产精品| 国产在线麻豆精品观看| 国产日本欧美一区二区三区在线| 欧美日韩精品在线观看| 美女啪啪无遮挡免费久久网站| 国产精品99久久久久久久久久久久| 国内精品久久久久国产盗摄免费观看完整版 | 性娇小13――14欧美| 亚洲一区二区精品在线观看| av成人免费观看| 99视频一区二区三区| 一个人看的www久久| 一区二区三区毛片| 一区二区三区av| 亚洲免费视频一区二区| 亚洲欧美日韩天堂一区二区| 亚洲午夜在线观看| 亚洲欧美区自拍先锋| 香蕉久久夜色精品国产| 久久精品二区| 美腿丝袜亚洲色图| 欧美日韩成人在线观看| 国产精品对白刺激久久久| 国产精品五月天| 国产一区二区精品丝袜| 在线播放日韩欧美| 亚洲欧洲中文日韩久久av乱码| 日韩一二三区视频| 亚洲调教视频在线观看| 午夜精品久久久久久久久久久久| 欧美亚洲视频| 欧美成人精品一区二区| 欧美日韩不卡在线| 国产精品久久久久77777| 国产精品色在线| 亚洲第一精品影视| 亚洲开发第一视频在线播放| 亚洲欧美清纯在线制服| 免费观看成人www动漫视频| 欧美日韩 国产精品| 国产精品久久婷婷六月丁香| 国内精品国产成人| 一本色道久久加勒比88综合| 欧美在线观看一区二区| 欧美激情综合在线| 国产亚洲欧美日韩日本| 日韩亚洲欧美综合| 性做久久久久久免费观看欧美| 男男成人高潮片免费网站| 国产精品国产一区二区| 亚洲成色www久久网站| 亚洲伊人久久综合| 欧美福利视频网站| 狠狠久久综合婷婷不卡| 亚洲一级黄色| 欧美国产在线视频| 另类图片综合电影| 国产精品亚洲美女av网站| 亚洲欧洲一区| 欧美呦呦网站| 国产精品爱啪在线线免费观看| 一区二区三区亚洲| 午夜在线一区二区| 欧美视频导航| 91久久久久久久久久久久久| 久久不射网站| 国产精品一区二区久激情瑜伽| 亚洲三级视频在线观看| 久久综合狠狠综合久久激情| 国产精品大片免费观看| 激情欧美国产欧美| 久久国产精品免费一区| 国产精品一区一区| 亚洲欧美另类久久久精品2019| 欧美区日韩区| 日韩午夜电影av| 欧美极品影院| 亚洲精品你懂的| 欧美国产成人在线| 亚洲日本精品国产第一区| 欧美成人午夜激情| 亚洲美女性视频| 欧美日韩精品一区二区天天拍小说 | 狠狠色综合播放一区二区| 午夜精品久久久久久99热软件| 欧美四级在线观看| 这里只有精品丝袜| 国产精品亚洲综合色区韩国| 欧美亚洲免费| 狠狠久久五月精品中文字幕| 蜜桃av一区二区| 亚洲美女网站| 国产精品日韩专区| 欧美在线观看视频一区二区| 国产一区在线播放| 美女黄色成人网| 日韩视频一区二区三区在线播放免费观看 | 91久久极品少妇xxxxⅹ软件| 欧美精品一线| 午夜在线一区| 在线成人欧美| 国产精品高清在线| 久久九九热re6这里有精品| 在线观看av不卡| 欧美日韩亚洲高清一区二区| 亚洲欧美日韩国产一区二区| 精品成人一区二区三区| 欧美人与性动交cc0o| 亚洲免费在线视频一区 二区| 国产一区二区三区的电影| 欧美69视频| 香蕉精品999视频一区二区 | 蜜臀av性久久久久蜜臀aⅴ| 日韩天天综合| 韩日精品视频一区| 欧美日韩国产小视频| 欧美一区二区三区视频免费播放| 亚洲二区精品| 欧美精品综合| 久久一区免费| 亚洲欧美久久久| 亚洲精美视频| 国产亚洲综合在线| 欧美日韩在线免费视频| 久久久久久久精| 亚洲欧美自拍偷拍| 亚洲精品亚洲人成人网| 国产精品夜夜嗨| 欧美精品aa| 久久手机精品视频| 欧美中在线观看| 亚洲一区精品视频| 一本久道久久综合婷婷鲸鱼| 在线观看视频一区二区| 国产精品乱子久久久久| 欧美理论在线播放| 蜜臀久久99精品久久久画质超高清| 午夜精品美女自拍福到在线| 亚洲精品日韩在线观看| 伊人激情综合| 国内精品久久久久久 | 一区二区在线观看视频| 国产欧美一区二区视频| 欧美性开放视频| 欧美日韩在线一区二区| 欧美激情第10页| 欧美69视频| 欧美精品v国产精品v日韩精品| 欧美mv日韩mv国产网站app| 亚洲欧美国产77777| 在线亚洲激情| a91a精品视频在线观看| 一区二区三区偷拍| 亚洲深夜福利| 午夜精品久久久久久久99水蜜桃 | 欧美—级a级欧美特级ar全黄| 久久女同精品一区二区| 久久婷婷麻豆| 欧美mv日韩mv国产网站| 欧美精品免费在线观看| 欧美女同视频| 国产精品网站视频| 国内精品久久久久影院色 | 亚洲国产成人在线| 亚洲精品免费一二三区| 亚洲一区二区三区免费视频| 亚洲欧美综合网| 久久久免费av| 欧美激情中文字幕乱码免费| 欧美日韩国产va另类| 国产精品久久久久久久久久久久久| 国产九区一区在线| 在线观看一区视频| 亚洲精品久久久久久一区二区| 一本色道久久综合亚洲精品按摩 | 久久久久久网站| 欧美刺激午夜性久久久久久久| 欧美日韩一级黄| 国产日产欧产精品推荐色| 精久久久久久| 一本色道久久综合亚洲精品高清| 亚洲专区免费| 女同性一区二区三区人了人一| 国产精品久久久99|