Iris Example PyTorch Implementation

Size: px
Start display at page:

Download "Iris Example PyTorch Implementation"

Transcription

1 Iris Example PyTorch Implementation February, 28 Iris Example using Pytorch.nn Using SciKit s Learn s prebuilt datset of Iris Flowers (which is in a numpy data format), we build a linear classifier in PyTorch.nn to predict what species of flower it is. We start with loading the dataset and viewing the dataset s properties. In []: from sklearn.datasets import load_iris iris_data = load_iris() features, pre_labels = iris_data.data, iris_data.target print (features[::]) #print every th element print (pre_labels[::]) #print every th element [[ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ]] [ ] As you can see above, the dataset is organised by the labels. So we need to shuffle the dataset so our model is able learn or have the data fitted appropriately. Before we shuffle the data, we need to do some data pre-processing.. Preprocessing labels to an array We convert the class indexes into an array. So as for example, for class[] it would look like [,, ]. We also convert it to a numpy array for better computation and memory. We need to apply

2 one-hot-encoding for the labels so our linear model is able to give is a probability of what flower it is In [2]: labels = [] for num in range(len(pre_labels)): if pre_labels[num] == : labels.append([,, ]) if pre_labels[num] == : labels.append([,, ]) if pre_labels[num] == 2: labels.append([,, ]) import numpy as np labels = np.array(labels, dtype = int)..2 Shuffling and splitting dataset into training and testing We import the prebuit function in sci-kit learn to split the dataset into training and testing. We also shuffle the data to ensure that our training set is top-notch in quality. We print the length of each split of the dataset to confirm that the split is appropriate. In [3]: from sklearn.model_selection import train_test_split feature_train, feature_test, labels_train, labels_test = train_test_split(features, labe print (len(feature_train)) print (len(feature_test)) Importing the necessary libraries and functions We import the PyTorch framework and all the necessary functions that comes along with it. We also assign our data to the PyTorch placeholder variables. We print the features and label tensors to see how it looks. In [4]: import torch import torch.nn as nn #PyTorch's module wrapper import torch.optim as optim #PyTorch's optimiser from torch.autograd import Variable #PyTorch's implementer of gradient descent and back import numpy as np import matplotlib.pyplot as plt #importing graph plotting functionality %matplotlib inline feature_train_v = Variable(torch.FloatTensor(feature_train), requires_grad = False) labels_train_v = Variable(torch.FloatTensor(labels_train), requires_grad = False) feature_test_v = Variable(torch.FloatTensor(feature_test), requires_grad = False) labels_test_v = Variable(torch.FloatTensor(labels_test), requires_grad = False) 2

3 print (feature_train_v[]) print (labels_train_v[]) [torch.floattensor of size 4]. As you can see from the above, for the th element of the tensor array; it is most likely of class..4 Defining the architecture, functions and parameters of our neural network The model consists of a linear layer and a softmax layer. We also define the loss function and the optimiser. The model will return three values of the likelihood of what kind of flower it is. The softmax feature will essentially convert the outputs of the linear layer to probability values in a nutshell. We use a binary cross entropy loss function to ensure that the model is learning in the correct manner (I still don t understand why we use a binary cross entropy loss function) In [5]: class LinearClassifier(nn.Module): def init (self): super(linearclassifier, self). init () self.h_layer = nn.linear(4, 3) self.s_layer = nn.softmax() def forward(self,x): y = self.h_layer(x) p = self.s_layer(y) return p model = LinearClassifier() #declaring the classifier to an object loss_fn = nn.bceloss() #calculates the loss optim = torch.optim.sgd(model.parameters(), lr =.)..5 Fitting the training data to the model In [6]: all_losses = [] for num in range(5): #5 iterations 3

4 pred = model(feature_train_v) #predict loss = loss_fn(pred, labels_train_v) #calculate loss all_losses.append(loss.data) optim.zero_grad() #zero gradients to not accumulate loss.backward() #update weights based on loss optim.step() #update optimiser for next iteration /anaconda3/envs/summer/lib/python3.5/site-packages/ipykernel_launcher.py:9: UserWarning: Implici if name == ' main ':..6 Visualising the loss over iterations In [7]: import matplotlib.pyplot as plt %matplotlib inline all_losses = np.array(all_losses, dtype = np.float) plt.plot(all_losses) plt.show() print(pred[3]) print(labels_train_v[3]) print(all_losses[-]).45 4

5 Looks like our model has converged towards zero in a very nice way! As you can see we have printed the 3rd element of the training set and looks like it can predict what class flower it is in that particular example. Now we validate our model to see how well it works on unseen data...7 Validating the data of our test set. Using sklearn s inbuilt metrics to evaluate how good our model; because we are lazy to code our own evaluation metric. In [8]: from sklearn.metrics import accuracy_score predicted_values = [] for num in range(len(feature_test_v)): predicted_values.append(model(feature_test_v[num])) /anaconda3/envs/summer/lib/python3.5/site-packages/ipykernel_launcher.py:9: UserWarning: Implici if name == ' main ': In [9]: score = for num in range(len(predicted_values)): if np.argmax(labels_test[num]) == np.argmax(predicted_values[num].data.numpy()): score = score + accuracy = float(score / len(predicted_values)) * print ('Testing Accuracy Score is ' + str(accuracy)) Testing Accuracy Score is. Looks like we got a pretty good linear classifier which can determine what flower it is depending on 4 features. Typically we do not expect such a high test accuracy value of % as real-life situations have a lot more variation. 5

In stochastic gradient descent implementations, the fixed learning rate η is often replaced by an adaptive learning rate that decreases over time,

In stochastic gradient descent implementations, the fixed learning rate η is often replaced by an adaptive learning rate that decreases over time, Chapter 2 Although stochastic gradient descent can be considered as an approximation of gradient descent, it typically reaches convergence much faster because of the more frequent weight updates. Since

More information

Lab Five. COMP Advanced Artificial Intelligence Xiaowei Huang Cameron Hargreaves. October 29th 2018

Lab Five. COMP Advanced Artificial Intelligence Xiaowei Huang Cameron Hargreaves. October 29th 2018 Lab Five COMP 219 - Advanced Artificial Intelligence Xiaowei Huang Cameron Hargreaves October 29th 2018 1 Decision Trees and Random Forests 1.1 Reading Begin by reading chapter three of Python Machine

More information

Lab Four. COMP Advanced Artificial Intelligence Xiaowei Huang Cameron Hargreaves. October 22nd 2018

Lab Four. COMP Advanced Artificial Intelligence Xiaowei Huang Cameron Hargreaves. October 22nd 2018 Lab Four COMP 219 - Advanced Artificial Intelligence Xiaowei Huang Cameron Hargreaves October 22nd 2018 1 Reading Begin by reading chapter three of Python Machine Learning until page 80 found in the learning

More information

ML/DL for Everyone with

ML/DL for Everyone with Sung Kim HKUST Code: https://github.com/hunkim/pytorchzerotoall Slides: http://bit.ly/pytorchzeroall ML/DL for Everyone with Lecture 6: Logistic Regression Call for Comments Please

More information

intro_mlp_xor March 26, 2018

intro_mlp_xor March 26, 2018 intro_mlp_xor March 26, 2018 1 Introduction to Neural Networks Some material from peterroelants Goal: understand neural networks so they are no longer a black box In [121]: # do all of the imports here

More information

Keras: Handwritten Digit Recognition using MNIST Dataset

Keras: Handwritten Digit Recognition using MNIST Dataset Keras: Handwritten Digit Recognition using MNIST Dataset IIT PATNA February 9, 2017 1 / 24 OUTLINE 1 Introduction Keras: Deep Learning library for Theano and TensorFlow 2 Installing Keras Installation

More information

Lecture Linear Support Vector Machines

Lecture Linear Support Vector Machines Lecture 8 In this lecture we return to the task of classification. As seen earlier, examples include spam filters, letter recognition, or text classification. In this lecture we introduce a popular method

More information

Frameworks in Python for Numeric Computation / ML

Frameworks in Python for Numeric Computation / ML Frameworks in Python for Numeric Computation / ML Why use a framework? Why not use the built-in data structures? Why not write our own matrix multiplication function? Frameworks are needed not only because

More information

CS4618: Artificial Intelligence I. Accuracy Estimation. Initialization

CS4618: Artificial Intelligence I. Accuracy Estimation. Initialization CS4618: Artificial Intelligence I Accuracy Estimation Derek Bridge School of Computer Science and Information echnology University College Cork Initialization In [1]: %reload_ext autoreload %autoreload

More information

Practical example - classifier margin

Practical example - classifier margin Support Vector Machines (SVMs) SVMs are very powerful binary classifiers, based on the Statistical Learning Theory (SLT) framework. SVMs can be used to solve hard classification problems, where they look

More information

A brief introduction to coding in Python with Anatella

A brief introduction to coding in Python with Anatella A brief introduction to coding in Python with Anatella Before using the Python engine within Anatella, you must first: 1. Install & download a Python engine that support the Pandas Data Frame library.

More information

Keras: Handwritten Digit Recognition using MNIST Dataset

Keras: Handwritten Digit Recognition using MNIST Dataset Keras: Handwritten Digit Recognition using MNIST Dataset IIT PATNA January 31, 2018 1 / 30 OUTLINE 1 Keras: Introduction 2 Installing Keras 3 Keras: Building, Testing, Improving A Simple Network 2 / 30

More information

Convolutional Neural Networks (CNN)

Convolutional Neural Networks (CNN) Convolutional Neural Networks (CNN) By Prof. Seungchul Lee Industrial AI Lab http://isystems.unist.ac.kr/ POSTECH Table of Contents I. 1. Convolution on Image I. 1.1. Convolution in 1D II. 1.2. Convolution

More information

Lab 16 - Multiclass SVMs and Applications to Real Data in Python

Lab 16 - Multiclass SVMs and Applications to Real Data in Python Lab 16 - Multiclass SVMs and Applications to Real Data in Python April 7, 2016 This lab on Multiclass Support Vector Machines in Python is an adaptation of p. 366-368 of Introduction to Statistical Learning

More information

Planar data classification with one hidden layer

Planar data classification with one hidden layer Planar data classification with one hidden layer Welcome to your week 3 programming assignment. It's time to build your first neural network, which will have a hidden layer. You will see a big difference

More information

Technical University of Munich. Exercise 8: Neural Networks

Technical University of Munich. Exercise 8: Neural Networks Technical University of Munich Chair for Bioinformatics and Computational Biology Protein Prediction I for Computer Scientists SoSe 2018 Prof. B. Rost M. Bernhofer, M. Heinzinger, D. Nechaev, L. Richter

More information

ML/DL for Everyone with

ML/DL for Everyone with Sung Kim HKUST Code: https://github.com/hunkim/pytorchzerotoall Slides: http://bit.ly/pytorchzeroall ML/DL for Everyone with Lecture 8: DataLoader Call for Comments Please feel free

More information

lof April 23, Improving performance of Local outlier factor with KD-Trees

lof April 23, Improving performance of Local outlier factor with KD-Trees lof April 23, 2014 1 Improving performance of Local outlier factor with KD-Trees Local outlier factor (LOF) is an outlier detection algorithm, that detects outliers based on comparing local density of

More information

Activity recognition and energy expenditure estimation

Activity recognition and energy expenditure estimation Activity recognition and energy expenditure estimation A practical approach with Python WebValley 2015 Bojan Milosevic Scope Goal: Use wearable sensors to estimate energy expenditure during everyday activities

More information

Analyze the work and depth of this algorithm. These should both be given with high probability bounds.

Analyze the work and depth of this algorithm. These should both be given with high probability bounds. CME 323: Distributed Algorithms and Optimization Instructor: Reza Zadeh (rezab@stanford.edu) TA: Yokila Arora (yarora@stanford.edu) HW#2 Solution 1. List Prefix Sums As described in class, List Prefix

More information

Ch.1 Introduction. Why Machine Learning (ML)?

Ch.1 Introduction. Why Machine Learning (ML)? Syllabus, prerequisites Ch.1 Introduction Notation: Means pencil-and-paper QUIZ Means coding QUIZ Why Machine Learning (ML)? Two problems with conventional if - else decision systems: brittleness: The

More information

TF Mutiple Hidden Layers: Regression on Boston Data

TF Mutiple Hidden Layers: Regression on Boston Data TF Mutiple Hidden Layers: Regression on Boston Data This is adapted from Frossard's tutorial (http://www.cs.toronto.edu/~frossard/post/tensorflow/). This approach is not batched, and the number of layers

More information

RAJESH KEDIA 2014CSZ8383

RAJESH KEDIA 2014CSZ8383 SIV895: Special Module on Intelligent Information Processing Project Report Title: Classification of Iris flower species: Analysis using Neural Network. Submitted By: RAJESH KEDIA 14CSZ8383 Date: -Apr-16

More information

Tutorial 1. Linear Regression

Tutorial 1. Linear Regression Tutorial 1. Linear Regression January 11, 2017 1 Tutorial: Linear Regression Agenda: 1. Spyder interface 2. Linear regression running example: boston data 3. Vectorize cost function 4. Closed form solution

More information

Perceptron: This is convolution!

Perceptron: This is convolution! Perceptron: This is convolution! v v v Shared weights v Filter = local perceptron. Also called kernel. By pooling responses at different locations, we gain robustness to the exact spatial location of image

More information

Foolbox Documentation

Foolbox Documentation Foolbox Documentation Release 1.2.0 Jonas Rauber & Wieland Brendel Jun 27, 2018 User Guide 1 Robust Vision Benchmark 3 1.1 Installation................................................ 3 1.2 Tutorial..................................................

More information

ARTIFICIAL INTELLIGENCE AND PYTHON

ARTIFICIAL INTELLIGENCE AND PYTHON ARTIFICIAL INTELLIGENCE AND PYTHON DAY 1 STANLEY LIANG, LASSONDE SCHOOL OF ENGINEERING, YORK UNIVERSITY WHAT IS PYTHON An interpreted high-level programming language for general-purpose programming. Python

More information

Derek Bridge School of Computer Science and Information Technology University College Cork. from sklearn.preprocessing import add_dummy_feature

Derek Bridge School of Computer Science and Information Technology University College Cork. from sklearn.preprocessing import add_dummy_feature CS4618: Artificial Intelligence I Gradient Descent Derek Bridge School of Computer Science and Information Technology University College Cork Initialization In [1]: %load_ext autoreload %autoreload 2 %matplotlib

More information

User Documentation Decision Tree Classification with Bagging

User Documentation Decision Tree Classification with Bagging User Documentation Decision Tree Classification with Bagging A decision tree is a flowchart-like structure in which each internal node represents a "test" on an attribute, each branch represents the outcome

More information

scikit-learn (Machine Learning in Python)

scikit-learn (Machine Learning in Python) scikit-learn (Machine Learning in Python) (PB13007115) 2016-07-12 (PB13007115) scikit-learn (Machine Learning in Python) 2016-07-12 1 / 29 Outline 1 Introduction 2 scikit-learn examples 3 Captcha recognize

More information

Introduction to Machine Learning. Useful tools: Python, NumPy, scikit-learn

Introduction to Machine Learning. Useful tools: Python, NumPy, scikit-learn Introduction to Machine Learning Useful tools: Python, NumPy, scikit-learn Antonio Sutera and Jean-Michel Begon September 29, 2016 2 / 37 How to install Python? Download and use the Anaconda python distribution

More information

EPL451: Data Mining on the Web Lab 5

EPL451: Data Mining on the Web Lab 5 EPL451: Data Mining on the Web Lab 5 Παύλος Αντωνίου Γραφείο: B109, ΘΕΕ01 University of Cyprus Department of Computer Science Predictive modeling techniques IBM reported in June 2012 that 90% of data available

More information

Neural Contextual Code Search Mina Lee & Sonia Kim

Neural Contextual Code Search Mina Lee & Sonia Kim Neural Contextual Code Search Mina Lee & Sonia Kim Big Code @ Facebook Summer 2018 Contents Motivation Domain Approach Experiments Discussion Motivation Motivation Context Query class CustomDataset(torch.utils.data.Dataset):...

More information

Identification Of Iris Flower Species Using Machine Learning

Identification Of Iris Flower Species Using Machine Learning Identification Of Iris Flower Species Using Machine Learning Shashidhar T Halakatti 1, Shambulinga T Halakatti 2 1 Department. of Computer Science Engineering, Rural Engineering College,Hulkoti 582205

More information

CSE 152 : Introduction to Computer Vision, Spring 2018 Assignment 5

CSE 152 : Introduction to Computer Vision, Spring 2018 Assignment 5 CSE 152 : Introduction to Computer Vision, Spring 2018 Assignment 5 Instructor: Ben Ochoa Assignment Published On: Wednesday, May 23, 2018 Due On: Saturday, June 9, 2018, 11:59 PM Instructions Review the

More information

nolearn Documentation

nolearn Documentation nolearn Documentation Release 0.6 Daniel Nouri September 06, 2016 Contents 1 Installation 3 2 Modules 5 2.1 nolearn.cache............................................ 5 2.2 nolearn.dbn.............................................

More information

SUPERVISED LEARNING WITH SCIKIT-LEARN. How good is your model?

SUPERVISED LEARNING WITH SCIKIT-LEARN. How good is your model? SUPERVISED LEARNING WITH SCIKIT-LEARN How good is your model? Classification metrics Measuring model performance with accuracy: Fraction of correctly classified samples Not always a useful metric Class

More information

Code Mania Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python:

Code Mania Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python: Code Mania 2019 Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python: 1. Introduction to Artificial Intelligence 2. Introduction to python programming and Environment

More information

Introduction to Machine Learning Prof. Anirban Santara Department of Computer Science and Engineering Indian Institute of Technology, Kharagpur

Introduction to Machine Learning Prof. Anirban Santara Department of Computer Science and Engineering Indian Institute of Technology, Kharagpur Introduction to Machine Learning Prof. Anirban Santara Department of Computer Science and Engineering Indian Institute of Technology, Kharagpur Lecture 14 Python Exercise on knn and PCA Hello everyone,

More information

Lab 10 - Ridge Regression and the Lasso in Python

Lab 10 - Ridge Regression and the Lasso in Python Lab 10 - Ridge Regression and the Lasso in Python March 9, 2016 This lab on Ridge Regression and the Lasso is a Python adaptation of p. 251-255 of Introduction to Statistical Learning with Applications

More information

SVM multiclass classification in 10 steps 17/32

SVM multiclass classification in 10 steps 17/32 SVM multiclass classification in 10 steps import numpy as np # load digits dataset from sklearn import datasets digits = datasets. load_digits () # define training set size n_samples = len ( digits. images

More information

MLXTEND. Mlxtend v Sebastian Raschka

MLXTEND. Mlxtend v Sebastian Raschka MLXTEND Mlxtend v0.4.1 Sebastian Raschka 1 2 CONTENTS Contents 0.0.1 Welcome to mlxtend s documentation!........... 19 0.1 Links.................................. 20 0.2 Examples...............................

More information

Scikit-plot Documentation

Scikit-plot Documentation Scikit-plot Documentation Release Reiichiro S. Nakano Feb 07, 2018 Contents 1 The quickest and easiest way to go from analysis... 1 2... to this. 3 2.1 First steps with Scikit-plot........................................

More information

CS229 Final Project: Predicting Expected Response Times

CS229 Final Project: Predicting Expected  Response Times CS229 Final Project: Predicting Expected Email Response Times Laura Cruz-Albrecht (lcruzalb), Kevin Khieu (kkhieu) December 15, 2017 1 Introduction Each day, countless emails are sent out, yet the time

More information

Latent Semantic Analysis. sci-kit learn. Vectorizing text. Document-term matrix

Latent Semantic Analysis. sci-kit learn. Vectorizing text. Document-term matrix Latent Semantic Analysis Latent Semantic Analysis (LSA) is a framework for analyzing text using matrices Find relationships between documents and terms within documents Used for document classification,

More information

python numpy tensorflow tutorial

python numpy tensorflow tutorial python numpy tensorflow tutorial September 11, 2016 1 What is Python? From Wikipedia: - Python is a widely used high-level, general-purpose, interpreted, dynamic programming language. - Design philosophy

More information

Predict the Likelihood of Responding to Direct Mail Campaign in Consumer Lending Industry

Predict the Likelihood of Responding to Direct Mail Campaign in Consumer Lending Industry Predict the Likelihood of Responding to Direct Mail Campaign in Consumer Lending Industry Jincheng Cao, SCPD Jincheng@stanford.edu 1. INTRODUCTION When running a direct mail campaign, it s common practice

More information

Assignment4. November 29, Follow the directions on https://www.tensorflow.org/install/ to install Tensorflow on your computer.

Assignment4. November 29, Follow the directions on https://www.tensorflow.org/install/ to install Tensorflow on your computer. Assignment4 November 29, 2017 1 CSE 252A Computer Vision I Fall 2017 1.1 Assignment 4 1.2 Problem 1: Install Tensorflow [2 pts] Follow the directions on https://www.tensorflow.org/install/ to install Tensorflow

More information

maxbox Starter 66 - Data Science with Max

maxbox Starter 66 - Data Science with Max //////////////////////////////////////////////////////////////////////////// Machine Learning IV maxbox Starter 66 - Data Science with Max There are two kinds of data scientists: 1) Those who can extrapolate

More information

Logistic Regression with a Neural Network mindset

Logistic Regression with a Neural Network mindset Logistic Regression with a Neural Network mindset Welcome to your first (required) programming assignment! You will build a logistic regression classifier to recognize cats. This assignment will step you

More information

Recurrent Neural Network

Recurrent Neural Network Recurrent Neural Network Table of Contents I. 1. Recurrent Neural Network (RNN) I. 1.1. Feedforward Network and Sequential Data II. 1.2. Structure of RNN III. 1.3. RNN with LSTM IV. 1.4. RNN and Sequential

More information

Search. The Nearest Neighbor Problem

Search. The Nearest Neighbor Problem 3 Nearest Neighbor Search Lab Objective: The nearest neighbor problem is an optimization problem that arises in applications such as computer vision, pattern recognition, internet marketing, and data compression.

More information

Neural networks. About. Linear function approximation. Spyros Samothrakis Research Fellow, IADS University of Essex.

Neural networks. About. Linear function approximation. Spyros Samothrakis Research Fellow, IADS University of Essex. Neural networks Spyros Samothrakis Research Fellow, IADS University of Essex About Linear function approximation with SGD From linear regression to neural networks Practical aspects February 28, 2017 Conclusion

More information

Prof. Dr. Rudolf Mathar, Dr. Arash Behboodi, Emilio Balda. Exercise 5. Friday, December 22, 2017

Prof. Dr. Rudolf Mathar, Dr. Arash Behboodi, Emilio Balda. Exercise 5. Friday, December 22, 2017 Fundamentals of Big Data Analytics Prof. Dr. Rudolf Mathar, Dr. Arash Behboodi, Emilio Balda Exercise 5 Friday, December 22, 2017 Problem 1. Discriminant Analysis for MNIST dataset (PyTorch) In this script,

More information

Scikit-plot Documentation

Scikit-plot Documentation Scikit-plot Documentation Release Reiichiro S. Nakano Sep 17, 2017 Contents 1 The quickest and easiest way to go from analysis... 1 2...to this. 3 2.1 First steps with Scikit-plot........................................

More information

Ch.1 Introduction. Why Machine Learning (ML)? manual designing of rules requires knowing how humans do it.

Ch.1 Introduction. Why Machine Learning (ML)? manual designing of rules requires knowing how humans do it. Ch.1 Introduction Syllabus, prerequisites Notation: Means pencil-and-paper QUIZ Means coding QUIZ Code respository for our text: https://github.com/amueller/introduction_to_ml_with_python Why Machine Learning

More information

Data Science and Machine Learning Essentials

Data Science and Machine Learning Essentials Data Science and Machine Learning Essentials Lab 3B Building Models in Azure ML By Stephen Elston and Graeme Malcolm Overview In this lab, you will learn how to use R or Python to engineer or construct

More information

from sklearn import tree from sklearn.ensemble import AdaBoostClassifier, GradientBoostingClassifier

from sklearn import tree from sklearn.ensemble import AdaBoostClassifier, GradientBoostingClassifier 1 av 7 2019-02-08 10:26 In [1]: import pandas as pd import numpy as np import matplotlib import matplotlib.pyplot as plt from sklearn import tree from sklearn.ensemble import AdaBoostClassifier, GradientBoostingClassifier

More information

Lecture 8: Grid Search and Model Validation Continued

Lecture 8: Grid Search and Model Validation Continued Lecture 8: Grid Search and Model Validation Continued Mat Kallada STAT2450 - Introduction to Data Mining with R Outline for Today Model Validation Grid Search Some Preliminary Notes Thank you for submitting

More information

Unsupervised Learning: K-means Clustering

Unsupervised Learning: K-means Clustering Unsupervised Learning: K-means Clustering by Prof. Seungchul Lee isystems Design Lab http://isystems.unist.ac.kr/ UNIST Table of Contents I. 1. Supervised vs. Unsupervised Learning II. 2. K-means I. 2.1.

More information

Accelerated Machine Learning Algorithms in Python

Accelerated Machine Learning Algorithms in Python Accelerated Machine Learning Algorithms in Python Patrick Reilly, Leiming Yu, David Kaeli reilly.pa@husky.neu.edu Northeastern University Computer Architecture Research Lab Outline Motivation and Goals

More information

Multi-Class Logistic Regression and Perceptron

Multi-Class Logistic Regression and Perceptron Multi-Class Logistic Regression and Perceptron Instructor: Wei Xu Some slides adapted from Dan Jurfasky, Brendan O Connor and Marine Carpuat MultiClass Classification Q: what if we have more than 2 categories?

More information

Machine Learning Part 1

Machine Learning Part 1 Data Science Weekend Machine Learning Part 1 KMK Online Analytic Team Fajri Koto Data Scientist fajri.koto@kmklabs.com Machine Learning Part 1 Outline 1. Machine Learning at glance 2. Vector Representation

More information

Deep Neural Networks Optimization

Deep Neural Networks Optimization Deep Neural Networks Optimization Creative Commons (cc) by Akritasa http://arxiv.org/pdf/1406.2572.pdf Slides from Geoffrey Hinton CSC411/2515: Machine Learning and Data Mining, Winter 2018 Michael Guerzhoy

More information

Derek Bridge School of Computer Science and Information Technology University College Cork

Derek Bridge School of Computer Science and Information Technology University College Cork CS4619: Artificial Intelligence II Overfitting and Underfitting Derek Bridge School of Computer Science and Information Technology University College Cork Initialization In [1]: %load_ext autoreload %autoreload

More information

Derek Bridge School of Computer Science and Information Technology University College Cork

Derek Bridge School of Computer Science and Information Technology University College Cork CS4619: Artificial Intelligence II Methodology Dere Bridge School of Computer Science and Information Technology University College Cor Initialization In [1]: %load_ext autoreload %autoreload 2 %matplotlib

More information

3 Types of Gradient Descent Algorithms for Small & Large Data Sets

3 Types of Gradient Descent Algorithms for Small & Large Data Sets 3 Types of Gradient Descent Algorithms for Small & Large Data Sets Introduction Gradient Descent Algorithm (GD) is an iterative algorithm to find a Global Minimum of an objective function (cost function)

More information

Goals: In [1]: import numpy as np. In [2]: from sklearn.svm import SVR. Introduction to the challenge

Goals: In [1]: import numpy as np. In [2]: from sklearn.svm import SVR.   Introduction to the challenge In [1]: import numpy as np import pandas as pd import os import warnings import time warnings.simplefilter("ignore") In [2]: from sklearn.svm import SVR from sklearn.linear_model import SGDRegressor, LinearRegression

More information

(2) Hypothesis Testing

(2) Hypothesis Testing (2) Hypothesis Testing March 1, 2016 In [4]: %matplotlib inline #python includes import sys #standard probability includes: import numpy as np #matrices and data structures import scipy.stats as ss #standard

More information

MATH 829: Introduction to Data Mining and Analysis Model selection

MATH 829: Introduction to Data Mining and Analysis Model selection 1/12 MATH 829: Introduction to Data Mining and Analysis Model selection Dominique Guillot Departments of Mathematical Sciences University of Delaware February 24, 2016 2/12 Comparison of regression methods

More information

About the Tutorial. Audience. Prerequisites. Copyright & Disclaimer. PyTorch

About the Tutorial. Audience. Prerequisites. Copyright & Disclaimer. PyTorch i About the Tutorial is an open source machine learning library for Python and is completely based on Torch. It is primarily used for applications such as natural language processing. is developed by Facebook's

More information

Training Neural Networks with Mixed Precision MICHAEL CARILLI CHRISTIAN SAROFEEN MICHAEL RUBERRY BEN BARSDELL

Training Neural Networks with Mixed Precision MICHAEL CARILLI CHRISTIAN SAROFEEN MICHAEL RUBERRY BEN BARSDELL Training Neural Networks with Mixed Precision MICHAEL CARILLI CHRISTIAN SAROFEEN MICHAEL RUBERRY BEN BARSDELL 1 THIS TALK Using mixed precision and Volta your networks can be: 1. 2-4x faster 2. half the

More information

UNSUPERVISED LEARNING IN PYTHON. Visualizing the PCA transformation

UNSUPERVISED LEARNING IN PYTHON. Visualizing the PCA transformation UNSUPERVISED LEARNING IN PYTHON Visualizing the PCA transformation Dimension reduction More efficient storage and computation Remove less-informative "noise" features... which cause problems for prediction

More information

Deep neural networks II

Deep neural networks II Deep neural networks II May 31 st, 2018 Yong Jae Lee UC Davis Many slides from Rob Fergus, Svetlana Lazebnik, Jia-Bin Huang, Derek Hoiem, Adriana Kovashka, Why (convolutional) neural networks? State of

More information

Model Selection Introduction to Machine Learning. Matt Gormley Lecture 4 January 29, 2018

Model Selection Introduction to Machine Learning. Matt Gormley Lecture 4 January 29, 2018 10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Model Selection Matt Gormley Lecture 4 January 29, 2018 1 Q&A Q: How do we deal

More information

Kaggle See Click Fix Model Description

Kaggle See Click Fix Model Description Kaggle See Click Fix Model Description BY: Miroslaw Horbal & Bryan Gregory LOCATION: Waterloo, Ont, Canada & Dallas, TX CONTACT : miroslaw@gmail.com & bryan.gregory1@gmail.com CONTEST: See Click Predict

More information

Adam Paszke, Sam Gross, Soumith Chintala, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia

Adam Paszke, Sam Gross, Soumith Chintala, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Adam Paszke, Sam Gross, Soumith Chintala, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Alban Desmaison, Andreas Kopf, Edward Yang, Zach Devito,

More information

Index. Umberto Michelucci 2018 U. Michelucci, Applied Deep Learning,

Index. Umberto Michelucci 2018 U. Michelucci, Applied Deep Learning, A Acquisition function, 298, 301 Adam optimizer, 175 178 Anaconda navigator conda command, 3 Create button, 5 download and install, 1 installing packages, 8 Jupyter Notebook, 11 13 left navigation pane,

More information

A. Python Crash Course

A. Python Crash Course A. Python Crash Course Agenda A.1 Installing Python & Co A.2 Basics A.3 Data Types A.4 Conditions A.5 Loops A.6 Functions A.7 I/O A.8 OLS with Python 2 A.1 Installing Python & Co You can download and install

More information

Effective Programming Practices for Economists. 10. Some scientific tools for Python

Effective Programming Practices for Economists. 10. Some scientific tools for Python Effective Programming Practices for Economists 10. Some scientific tools for Python Hans-Martin von Gaudecker Department of Economics, Universität Bonn A NumPy primer The main NumPy object is the homogeneous

More information

Derek Bridge School of Computer Science and Information Technology University College Cork

Derek Bridge School of Computer Science and Information Technology University College Cork CS468: Artificial Intelligence I Ordinary Least Squares Regression Derek Bridge School of Computer Science and Information Technology University College Cork Initialization In [4]: %load_ext autoreload

More information

Homework 2. Due: March 2, 2018 at 7:00PM. p = 1 m. (x i ). i=1

Homework 2. Due: March 2, 2018 at 7:00PM. p = 1 m. (x i ). i=1 Homework 2 Due: March 2, 2018 at 7:00PM Written Questions Problem 1: Estimator (5 points) Let x 1, x 2,..., x m be an i.i.d. (independent and identically distributed) sample drawn from distribution B(p)

More information

Natural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu

Natural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu Natural Language Processing CS 6320 Lecture 6 Neural Language Models Instructor: Sanda Harabagiu In this lecture We shall cover: Deep Neural Models for Natural Language Processing Introduce Feed Forward

More information

Lab 15 - Support Vector Machines in Python

Lab 15 - Support Vector Machines in Python Lab 15 - Support Vector Machines in Python November 29, 2016 This lab on Support Vector Machines is a Python adaptation of p. 359-366 of Introduction to Statistical Learning with Applications in R by Gareth

More information

Interactive Mode Python Pylab

Interactive Mode Python Pylab Short Python Intro Gerald Schuller, Nov. 2016 Python can be very similar to Matlab, very easy to learn if you already know Matlab, it is Open Source (unlike Matlab), it is easy to install, and unlike Matlab

More information

Classification and K-Nearest Neighbors

Classification and K-Nearest Neighbors Classification and K-Nearest Neighbors Administrivia o Reminder: Homework 1 is due by 5pm Friday on Moodle o Reading Quiz associated with today s lecture. Due before class Wednesday. NOTETAKER 2 Regression

More information

Contents Machine Learning concepts 4 Learning Algorithm 4 Predictive Model (Model) 4 Model, Classification 4 Model, Regression 4 Representation

Contents Machine Learning concepts 4 Learning Algorithm 4 Predictive Model (Model) 4 Model, Classification 4 Model, Regression 4 Representation Contents Machine Learning concepts 4 Learning Algorithm 4 Predictive Model (Model) 4 Model, Classification 4 Model, Regression 4 Representation Learning 4 Supervised Learning 4 Unsupervised Learning 4

More information

Clustering algorithms and autoencoders for anomaly detection

Clustering algorithms and autoencoders for anomaly detection Clustering algorithms and autoencoders for anomaly detection Alessia Saggio Lunch Seminars and Journal Clubs Université catholique de Louvain, Belgium 3rd March 2017 a Outline Introduction Clustering algorithms

More information

PYTHON DATA VISUALIZATIONS

PYTHON DATA VISUALIZATIONS PYTHON DATA VISUALIZATIONS from Learning Python for Data Analysis and Visualization by Jose Portilla https://www.udemy.com/learning-python-for-data-analysis-and-visualization/ Notes by Michael Brothers

More information

Linear discriminant analysis and logistic

Linear discriminant analysis and logistic Practical 6: classifiers Linear discriminant analysis and logistic This practical looks at two different methods of fitting linear classifiers. The linear discriminant analysis is implemented in the MASS

More information

Machine Learning 13. week

Machine Learning 13. week Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of

More information

Unsupervised Learning

Unsupervised Learning Deep Learning for Graphics Unsupervised Learning Niloy Mitra Iasonas Kokkinos Paul Guerrero Vladimir Kim Kostas Rematas Tobias Ritschel UCL UCL/Facebook UCL Adobe Research U Washington UCL Timetable Niloy

More information

pescador Documentation

pescador Documentation pescador Documentation Release Brian McFee and Eric Humphrey July 28, 2016 Contents 1 Simple example 1 1.1 Batch generators............................................. 1 1.2 StreamLearner..............................................

More information

Predicting Diabetes using Neural Networks and Randomized Optimization

Predicting Diabetes using Neural Networks and Randomized Optimization Predicting Diabetes using Neural Networks and Randomized Optimization Kunal Sharma GTID: ksharma74 CS 4641 Machine Learning Abstract This paper analysis the following randomized optimization techniques

More information

Python for R Users. By Chandan Routray As a part of internship at

Python for R Users. By Chandan Routray As a part of internship at for Users By Chandan outray As a part of internship at www.decisionstats.com Basic Commands Functions Downloading and installing a package install.packages('name') pip install name Load a package library('name')

More information

Problem Based Learning 2018

Problem Based Learning 2018 Problem Based Learning 2018 Introduction to Machine Learning with Python L. Richter Department of Computer Science Technische Universität München Monday, Jun 25th L. Richter PBL 18 1 / 21 Overview 1 2

More information

Machine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center

Machine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center Machine Learning With Python Bin Chen Nov. 7, 2017 Research Computing Center Outline Introduction to Machine Learning (ML) Introduction to Neural Network (NN) Introduction to Deep Learning NN Introduction

More information

Log- linear models. Natural Language Processing: Lecture Kairit Sirts

Log- linear models. Natural Language Processing: Lecture Kairit Sirts Log- linear models Natural Language Processing: Lecture 3 21.09.2017 Kairit Sirts The goal of today s lecture Introduce the log- linear/maximum entropy model Explain the model components: features, parameters,

More information

Autoencoder. 1. Unsupervised Learning. By Prof. Seungchul Lee Industrial AI Lab POSTECH.

Autoencoder. 1. Unsupervised Learning. By Prof. Seungchul Lee Industrial AI Lab  POSTECH. Autoencoder By Prof. Seungchul Lee Industrial AI Lab http://isystems.unist.ac.kr/ POSTECH Table of Contents I. 1. Unsupervised Learning II. 2. Autoencoders III. 3. Autoencoder with TensorFlow I. 3.1. Import

More information

wget

wget CIFAR 10 In 1]: %matplotlib inline %reload_ext autoreload %autoreload 2 The CIFAR-10 dataset consists of 60000 32x32 color images in 10 classes, with 6000 images per class. There are 50000 training images

More information