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
Dimitris Spathis
January 17, 2016
Research
0
390
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
690
Wikipedia graph network analysis
sdimi
0
150
Character level LSTM Recurrent Neural Networks for language and music modeling
sdimi
0
300
Topic modeling and summarization of live TV shows via Twitter
sdimi
0
140
Diagnosing respiratory diseases with machine learning
sdimi
0
160
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
電力システム最適化入門
mickey_kubo
1
920
When Submarine Cables Go Dark: Examining the Web Services Resilience Amid Global Internet Disruptions
irvin
0
300
一人称視点映像解析の最先端(MIRU2025 チュートリアル)
takumayagi
6
3.5k
【緊急警告】日本の未来設計図 ~沈没か、再生か。国民と断行するラストチャンス~
yuutakasan
0
150
[輪講] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
nk35jk
2
990
大規模な2値整数計画問題に対する 効率的な重み付き局所探索法
mickey_kubo
1
360
Vision and LanguageからのEmbodied AIとAI for Science
yushiku
PRO
1
530
不確実性下における目的と手段の統合的探索に向けた連続腕バンディットの応用 / iot70_gp_rff_mab
monochromegane
2
170
Language Models Are Implicitly Continuous
eumesy
PRO
0
230
[CV勉強会@関東 CVPR2025] VLM自動運転model S4-Driver
shinkyoto
2
480
Cross-Media Information Spaces and Architectures
signer
PRO
0
240
AIスパコン「さくらONE」のLLM学習ベンチマークによる性能評価 / SAKURAONE LLM Training Benchmarking
yuukit
0
340
Featured
See All Featured
Context Engineering - Making Every Token Count
addyosmani
3
49
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.9k
Large-scale JavaScript Application Architecture
addyosmani
512
110k
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
656
61k
Done Done
chrislema
185
16k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
33
2.4k
Build The Right Thing And Hit Your Dates
maggiecrowley
37
2.9k
4 Signs Your Business is Dying
shpigford
184
22k
Producing Creativity
orderedlist
PRO
347
40k
Building Flexible Design Systems
yeseniaperezcruz
328
39k
Side Projects
sachag
455
43k
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