Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Image recognition of handwritten digits in MNIS...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Dimitris Spathis
January 17, 2016
Research
0
410
Image recognition of handwritten digits in MNIST and flower classification in IRIS dataset
Code available here
https://github.com/sdimi/handwritten-digits-recognition
Dimitris Spathis
January 17, 2016
Tweet
Share
More Decks by Dimitris Spathis
See All by Dimitris Spathis
Song analysis "Jueves - La Oreja de Van Gogh "
sdimi
0
730
Wikipedia graph network analysis
sdimi
0
160
Character level LSTM Recurrent Neural Networks for language and music modeling
sdimi
0
310
Topic modeling and summarization of live TV shows via Twitter
sdimi
0
150
Diagnosing respiratory diseases with machine learning
sdimi
0
170
Detecting Irony on Greek Political Tweets: A Text Mining Approach
sdimi
0
120
Greece Unknown Facts
sdimi
1
190
Glocal News - Discover Top Local News, Globally.
sdimi
0
200
Responsive Web - Mobile First. An overview.
sdimi
1
190
Other Decks in Research
See All in Research
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
akihiro_kokubo
PRO
66
37k
2026-01-30-MandSL-textbook-jp-cos-lod
yegusa
0
230
A History of Approximate Nearest Neighbor Search from an Applications Perspective
matsui_528
1
160
財務諸表監査のための逐次検定
masakat0
1
250
An Open and Reproducible Deep Research Agent for Long-Form Question Answering
ikuyamada
0
280
ForestCast: Forecasting Deforestation Risk at Scale with Deep Learning
satai
3
400
Akamaiのキャッシュ効率を支えるAdaptSizeについての論文を読んでみた
bootjp
1
450
When Learned Data Structures Meet Computer Vision
matsui_528
1
2.9k
ペットのかわいい瞬間を撮影する オートシャッターAIアプリへの スマートラベリングの適用
mssmkmr
0
270
Pythonでジオを使い倒そう! 〜それとFOSS4G Hiroshima 2026のご紹介を少し〜
wata909
0
1.3k
LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
satai
3
470
ウェブ・ソーシャルメディア論文読み会 第36回: The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents (EMNLP, 2025)
hkefka385
0
160
Featured
See All Featured
Test your architecture with Archunit
thirion
1
2.2k
Producing Creativity
orderedlist
PRO
348
40k
Six Lessons from altMBA
skipperchong
29
4.2k
GitHub's CSS Performance
jonrohan
1032
470k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
231
22k
The Limits of Empathy - UXLibs8
cassininazir
1
220
Understanding Cognitive Biases in Performance Measurement
bluesmoon
32
2.8k
Claude Code どこまでも/ Claude Code Everywhere
nwiizo
61
52k
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
460
How to Think Like a Performance Engineer
csswizardry
28
2.5k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
5.8k
Stop Working from a Prison Cell
hatefulcrawdad
273
21k
Transcript
Αναγνώριση χειρόγραφων χαρακτήρων στο MNIST dataset & φυτών στο IRIS
dataset με μεθόδους μηχανικής μάθησης Δημήτρης Σπαθής Εξαμηνιαία εργασία – Ιαν 2016 Υπολογιστική Νοημοσύνη – Στατιστική Μάθηση Καθ.: Αναστάσιος Τέφας
MNIST dataset 70.000 εικόνες 28 x 28 pixel 784 διαστάσεις
60.000 train 10.000 test {0,1,2,..9} multi-class
Εργαλεία Python python.org Scikit – learn scikit-learn.org Matplotlib matplotlib.org Numpy
numpy.org
Προεπεξεργασία δεδομένων Ανακάτεμα δειγμάτων X, y = shuffle(mnist.data, mnist.target) Κανονικοποίηση
pixels [0,1] X_train, y_train = np.float32(X[:60000])/ 255., np.float32(y[:60000])
Κρατάμε 90 components 90,3% της αρχικής πληροφορίας PCA – Μείωση
Διάστασης (784 → 90)
Εκπαίδευση SVM fitting classifier = svm.SVC(gamma=0.01, C=3, kernel='rbf') 5 Cross
validation cross_validation.cross_val_score(classifier, X_train, y_train, cv=5)
Αποτελέσματα εκπαίδευσης
Παραδείγματα ταξινόμησης
Μείωση Διάστασης Kernel PCA (784 → 300) kpca = KernelPCA(kernel="rbf",n_components=300
, gamma=1) LDA (300 → 9) lda = LDA() #should keep [classes – 1] components
Nearest Classifier K Nearest Neighbor clf = neighbors.KNeighborsClassifier(n_neighbors=5) Nearest Centroid
classifier = NearestCentroid(metric='euclidean', shrink_threshold=None)
Αποτελέσματα εκπαίδευσης
Embedding για Μείωση Διάστασης (784 → 2) Spectral Embedding manifold.SpectralEmbedding
(n_components=2, affinity='nearest_neighbors', gamma=None, random_state=None, eigen_solver=None, n_neighbors=5) Isomap Embedding manifold.Isomap(n_neighbors=5, n_components=2)
Spectral Clustering Kρατάμε 5000 δείγματα για οπτικοποίηση Spectral Clustering cluster.SpectralClustering(n_clusters=10,
eigen_solver='arpack', affinity="nearest_neighbors")
None
None
Αποτελέσματα clustering
IRIS dataset 150 λουλούδια 4 διαστάσεις sepal length sepal width
petal length petal width 3 κλάσεις Iris Setosa Iris Versicolour Iris Virginica
Αποτελέσματα SVM εκπαίδευσης
SVM fine-tuning C
SVM fine-tuning Degree
SVM fine-tuning Gamma
Μείωση Διάστασης
None
Αποτελέσματα clustering & embedding
None
None
Further work Kernel PCA – Memory Errors Incremental PCA Grid
Search Deep Architectures Distributed / Parallel MapReduce / Spark Κώδικας σύντομα στο github.com/sdimi