OpenCV 3 Pythonilla
Image – OpenCV BGR : Matplotlib RGB
Basic image operations-pixel access
iPython-signaalinkäsittely numpy I – FFT: llä
signaalinkäsittely numpy I-FFT: llä ja DFT: llä Sinille, neliöaalloille, unitpulselle ja satunnaissignaalille
signaalinkäsittely NumPy II-Image Fourier-muunnoksella : FFT & DFT
Kuvan Käänteinen Fourier-muunnos alipäästösuodattimella: cv2.idft ()
Image Histogram
Video Capture and Switching colourspaces-RGB / HSV
Adaptive Thresholding-Otsu ’ s clustering-based image thresholding
Edge Detection-Sobel and Laplacian ytimet
Canny Edge Detection
Hough Transform-Circles
vedenjakaja algoritmi: Marker-based Segmentation I
Image noise reduction: Non-local Means denoising algorithm
Image object detection : Kasvojentunnistus Haar – Kaskadiluokittajien avulla
Image segmentation – Foreign extraction Grabcut algorithm based on graph cuts
Image Reconstruction – Inpainting (Interpolation) – Fast Marching Methods
Video : Mean shift object tracking
Machine Learning : Clustering-K – Means clustering I
Machine Learning : Clustering-K – Means clustering II
Machine Learning : Classification-k-nearest neighbors (k-nn) algorithm

Machine Learning with scikit-learn

scikit-learn installation
scikit-learn : Features and feature extraction – iris dataset
scikit-learn : Machine Learning Quick Preview
scikit-learn : Data Preprocessing I – Missing / Categorical data
scikit-learn : Data Preprocessing II – Partitioning a dataset / Feature scaling / Feature Selection / Regularisation
scikit-learn : Data Preprocessing III – Dimensionality reduction vis Sequential feature selection / Assessing feature importance via random forests
Data Compression via Dimensionality Reduction I – Principal component analysis (PCA)
skikit-Opi : Data Compression via Dimensionality Reduction II – Linear Discriminant Analysis (Lda)
scikit-learn : Data Compression via Dimensionality Reduction III – Nonlinear mappings via kernel principal component (KPCA) analysis
scikit-learn : Logistic Regression, Overfitting & regularisation
scikit-learn : valvottu oppiminen & valvomaton oppiminen – esim. valvomaton PCA-mitoituksen vähentäminen Iris – tietokokonaisuudella
scikit-learn : valvomaton_learning-kmeans clustering Iris-tietokokonaisuudella
scikit-learn : Lineaarisesti erotettava Data – lineaarinen malli & (Gaussin) radial basis function kernel (RBF kernel)
scikit-learn : Decision Tree Learning I – Entropy, Gini, and Information Gain
scikit-learn : Decision Tree Learning II – Construction the Decision Tree
scikit-learn : Random Decision Forests Classification
scikit-learn : Support Vector Machines (SVM)
scikit-learn : Support Vector Machines (SVM) II
flask with embedded machine learning I : serializing with pickle and db setup
flask with embedded Machine Learning II : Basic Flask App
Flask with Embedded Machine Learning III : Embedding Classifier
Flask with Embedded Machine Learning IV : Deploy
Flask with Embedded Machine Learning V : luokittelijan päivittäminen
scikit-Opi : Näyte roskapostisuodattimesta käyttäen SVM-luokittelua hyvä tai huono

Koneoppimisalgoritmeja ja-käsitteitä

Eräoppimisalgoritmi
yksikerroksinen neuroverkko-Perceptron-malli Iris-tietokokonaisuudessa käyttäen Heaviside step activation-funktiota
yksikerroksinen neuroverkko – Adaptive Linear Neuron using linear (identity) activation function with batch gradient descent method
yksikerroksinen neuroverkko-Adaptive Linear Neuron using linear (identity) activation with batch gradient descent method : Adaptive Linear Neuron using linear (identity) activation function with stokastic gradient descent (SGD)
Logistic Regression
VC (Vapnik-Chervonenkis) Dimension and Shatter
Bias-variance tradeoff
Maximum likability Estimation (MLE)
Neural Networks with backropagation for XOR using one hidden layer
minHash
TF-idf weight
Natural Language Processing (NLP): Sentimental Analysis I (IMDb & bag-of-Words)
Natural Language Processing (NLP): Sentimental Analysis II (tokenization, stemming, and stop words)
Natural Language Processing (NLP): Tunteanalyysi III (koulutus & cross validation)
Natural Language Processing (NLP): Tunteanalyysi IV (Out-of-core)
local-Sensitive Hashing (LSH) using Kosine Distance (Cosine Similarity)

Artificial Neural Networks (ANN)

Sources are available at Github – Jupyter notebook files
1. Johdanto
2. Eteenpäin etenevä
3. Gradient Descent
4. Virheiden repropagaatio
5. Tarkistetaan gradientti
6. Training via bfgs
7. Overfitting & Regularisation
8. Syväoppiminen I : Kuvantunnistus (kuvan lataaminen)
9. Deep Learning II: Image Recognition (Image classification)
10-Deep Learning III: Deep Learning III : Theano, TensorFlow ja Keras