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
400
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
710
Wikipedia graph network analysis
sdimi
0
150
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
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
EarthSynth: Generating Informative Earth Observation with Diffusion Models
satai
3
380
EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
satai
3
230
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
2
690
EOGS: Gaussian Splatting for Efficient Satellite Image Photogrammetry
satai
4
660
MIRU2025 チュートリアル講演「ロボット基盤モデルの最前線」
haraduka
15
8.9k
令和最新技術で伝統掲示板を再構築: HonoX で作る型安全なスレッドフロート型掲示板 / かろっく@calloc134 - Hono Conference 2025
calloc134
0
270
問いを起点に、社会と共鳴する知を育む場へ
matsumoto_r
PRO
0
660
国際論文を出そう!ICRA / IROS / RA-L への論文投稿の心構えとノウハウ / RSJ2025 Luncheon Seminar
koide3
10
5.5k
論文読み会 SNLP2025 Learning Dynamics of LLM Finetuning. In: ICLR 2025
s_mizuki_nlp
0
280
RHO-1: Not All Tokens Are What You Need
sansan_randd
1
190
情報技術の社会実装に向けた応用と課題:ニュースメディアの事例から / appmech-jsce 2025
upura
0
210
説明可能な機械学習と数理最適化
kelicht
0
190
Featured
See All Featured
Become a Pro
speakerdeck
PRO
29
5.6k
The Invisible Side of Design
smashingmag
302
51k
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
10
600
Mobile First: as difficult as doing things right
swwweet
225
10k
jQuery: Nuts, Bolts and Bling
dougneiner
65
7.9k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
31
2.7k
Building Flexible Design Systems
yeseniaperezcruz
329
39k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
RailsConf 2023
tenderlove
30
1.3k
KATA
mclloyd
PRO
32
15k
The Cult of Friendly URLs
andyhume
79
6.6k
Designing Experiences People Love
moore
142
24k
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