Construct a Convolutional Neural Network with Python

Slides:



Advertisements
Similar presentations
Lecture 2: Caffe: getting started Forward propagation
Advertisements

Spatial Pyramid Pooling in Deep Convolutional
Computer Go : A Go player Rohit Gurjar CS365 Project Presentation, IIT Kanpur Guided By – Prof. Amitabha Mukerjee.
Dr. Z. R. Ghassabi Spring 2015 Deep learning for Human action Recognition 1.
CS 189 Brian Chu Slides at: brianchu.com/ml/
MLSLP-2012 Learning Deep Architectures Using Kernel Modules (thanks collaborations/discussions with many people) Li Deng Microsoft Research, Redmond.
ConvNets for Image Classification
語音訊號處理之初步實驗 NTU Speech Lab 指導教授: 李琳山 助教: 熊信寬
Deep Learning Overview Sources: workshop-tutorial-final.pdf
Assignment 4: Deep Convolutional Neural Networks
Tofik AliPartha Pratim Roy Department of Computer Science and Engineering Indian Institute of Technology Roorkee CVIP-WM 2017 Paper ID 172 Word Spotting.
Sentiment analysis using deep learning methods
Unsupervised Learning of Video Representations using LSTMs
Demo.
Convolutional Neural Network
Environment Generation with GANs
Artificial Neural Networks
Computer Science and Engineering, Seoul National University
DeepCount Mark Lenson.
Applications of Deep Learning and how to get started with implementation of deep learning Presentation By : Manaswi Advisor : Dr.Chinmay.
Lecture 24: Convolutional neural networks
Lecture 25: Backprop and convnets
Classification with Perceptrons Reading:
Natural Language Processing of Knee MRI Reports
Lecture 5 Smaller Network: CNN
Convolution Neural Networks
Urban Sound Classification with a Convolution Neural Network
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Dynamic Routing Using Inter Capsule Routing Protocol Between Capsules
Image Question Answering
Introduction to Convolutional Neural Network (CNN/ConvNET)-insights from amateur George (Tian Zhou)
Handwritten Digits Recognition
Bird-species Recognition Using Convolutional Neural Network
Convolutional Neural Networks
Introduction to Neural Networks
Tensorflow in Deep Learning
A Comparative Study of Convolutional Neural Network Models with Rosenblatt’s Brain Model Abu Kamruzzaman, Atik Khatri , Milind Ikke, Damiano Mastrandrea,
Counting in Dense Crowds using Deep Learning
Deep Learning Hierarchical Representations for Image Steganalysis
Road Traffic Sign Recognition
Face Recognition with Neural Networks
network of simple neuron-like computing elements
MNIST Dataset Training with Tensorflow
Implementation of neural gas on Cell Broadband Engine
CSC 578 Neural Networks and Deep Learning
Detecting Myocardial Infarctions (Heart Attack) using Neural Network
Age and Gender Classification using Convolutional Neural Networks
Neural Networks Geoff Hulten.
On Convolutional Neural Network
Machine learning Empirical Performance Analysis
Forward and Backward Max Pooling
ECE/CS/ME 539 Artificial Neural Networks Final Project
Object Tracking: Comparison of
Analysis of Trained CNN (Receptive Field & Weights of Network)
Coding neural networks: A gentle Introduction to keras
Problems with CNNs and recent innovations 2/13/19
ImageNet Classification with Deep Convolutional Neural Networks
Deep Learning Authors: Yann LeCun, Yoshua Bengio, Geoffrey Hinton
Sketch Object Prediction
CIS 519 Recitation 11/15/18.
Deep Object Co-Segmentation
DRC with Deep Networks Tanmay Lagare, Arpit Jain, Luis Francisco,
Neural Machine Translation using CNN
Object Detection Implementations
CRCV REU 2019 Kara Schatz.
Example of training and deployment of deep convolutional neural networks. Example of training and deployment of deep convolutional neural networks. During.
CSC 578 Neural Networks and Deep Learning
Principles of Back-Propagation
Directional Occlusion with Neural Network
Presentation transcript:

Construct a Convolutional Neural Network with Python Le Li 31446468 ll393@njit.edu

Abstract The structure of the CNN The Parameters can be modified to adjust CNN Data Set : MNIST Baseline Model Result Comparison Shortcomings

A Three-layer Convolutional Neural Network The Cnvolutional Neural Network has one convolutional layer, one pooling layer, one Fully Connected layer, and finally passes through the Softmax layer.

A Three-layer Convolutional Neural Network Pooling Layer: The pooling size is 2*2 Pooling type: Max_pooling Mean_pooling Activation Function: Tanh:

Parameters You can adjust CNN attributes by changing the parameters C_SIZE : The size of the convolution kernel MAX_ITER_NUM = The iteration number of training train_num = The number of images to be used in training set. Test_num = The numbers of images to be used in test set data_num = train_num + Test_num cLyNum = The number of convolution kernels fLyNum = Number of fully connected neurons

Data Set There are 10,000 images from MNIST in the data set. Using 8,000 images as training set and 2000 as test set. The image size is 28*28. Labels are stored separately in a text file in the folder.

Baseline Model: Support Vector Machine (sk.learn LinearSVC, C=0.1) Cross Validation: Perform cross-validations with 8,000 images. Randomly select 80% of the images for training and 20% of the images for testing each time. Prediction: Using 2000 images of the data set for prediction and compute the accuracy.

Result Comparison The accuracy of prediction. CNN SVM(C=0.1) 8000 images for training and 2000 images for testing. CNN SVM(C=0.1) 20 training iterations 88% 90% 30 training iterations 92% CNN: 2*2 Mean-Pooling; 30 5*5 Convolution Kernels; Tanh activation function; 100 fully connected neurons

Shortcomings This self-built CNN has some shortcomings: Only 3 layers: one convolutional layer, one pooling layer and one Fully Connected layer, If you want to add a new layer, you need to modify the code. The program runs very slowly. It runs more than 30 minutes for training with 1000 images in 20 iterations. The accuracy has only been around 0.9.

Thanks !