Questions? 91-7034206363, 7034256363, 7034286363, 6238743273

Registered with Ministry Of Corporate Affairs - Government of India,
(CIN: U72900KL2016PTC046479, Dated: 05/08/2016)

Machine Learning Syllabus

Machine Learning (2 Months)

  • Statistics for data science, Response variables, Mean, Variance, Covariance, Beta, Alpha, Distributions
  • Normal Distribution, Link function, Logistic function, Logit function, Binomial, Poisoon, Chi Test, Anova, Use cases
  • SKlearn, Regression, Linear Regression, Multi-linear Regression, Classification
  • Navebays classification, Decision Tree, Random Forest, KNN, Clustering, K-Means,
  • Training data sets, over-fitting, under-fitting, cross-validation, Regularities
  • Variance, Bias, Performance measures, Bias Variance Tradeoff
  • Accuracy, Precesion, Recall, Sensitivity, Estimator, Visualization of training results
  • linear least squares, cost or loss function, Residuals, Residual sum of squares
  • least squares, Evalulating Model, calculate R-Squared, Regression Vector, Evolving Model
  • Finding Beta Vector, Calculating coefficients, Finding performance, Polynomial Regression
  • Compare Polynomial and Linear Regression, Quadratic and Cubic difference, regression curve
  • Nth Degree Polinomial, Regularization, Ridge Regression, Effect of Ridge regression
  • Apply Ridge regression, Lasso Regression, Elastic Net Regression, train/test split
  • Fitting evaluation technique, Validation, k-fold cross validation, Leave one out cross validation
  • Gradient Descent, Derivative of loss function, Learning rate, when to use GD
  • Stochastic Gradient Descent, Scaling features, Feature Extraction and Preprocessing
  • Label encoder, One-Hot encode, Extracting features from text, bag-of-words, Corpus, NLTK, Text processing, WordVect
  • Feature Vector, Tokenization, Document Similarity, Euclidian Distance, Semantic equivalent of documents
  • Sparse Vectors, Curse of Dimensionality, Hughes effect, Effect of adding dimensionality
  • Stop word filterning, Stemming and lemmatisation, Determiningl Lemma, TF-IDF weights, TF-IDF featurization
  • Logarithmically scalled frequencies, Augmented frequencies, Normalization, Inverse Document Frequency
  • hash trick, HashVectorizer, Computer Vision, Face detection, Extracting features from pixel densities
  • OCR, Hanwritten letter recognition, Feature vector of an image, Image featurization, Deep Learning from images
  • Extracting points of objects, Point of interestes, SIFT, SURF, mohotas, Data Standardization, Normalization
  • Unit scaling, z-score scaling, Standard scaler, Domination Feature, Logistic Regression
  • Binary classification, Confusion Matrix, Visualiz confusion matrix, Reading confusion matrix, Accuracy
  • Precesion and Recall, F1 measure, ROC AUC, Plot AUC, Hperparameters, grid search, tuning model
  • Multi-class classification, Sentimental Analysis, Medical data analysis, Multi-label classification performance
  • Jaccard Similarity, Hamming Loss, Non Linear classification and Regression, agglomerative and divisive clustering
  • Building Trees, Similarity Impact, Purity of Decesion Trees, Binary classification problem use case
  • Measure of Purity, Gini Impurity, Classification error, Training decesion trees, Entropy, Gain Ratio and over fitting
  • Pruning, Post Pruning, Titanic Disastor Analytics Use case, Data Exploration, Modeling, Decision Tree classifier
  • Render DT Pic, Ensemble, Random guessing, Ada Boost, Tree ensembling, Random input and combinations
  • Bagging, Boosting, Dimensionality Reduction, Extremely Randomised Trees, Overfitting RF, Stacking and Blending
  • Stacked encoder, Eager Learners, Lazy Learners, Classification Distortions, Local optima, elbow method, Evaluating clusters
  • silhouette coefficient, Image quantization, Dimensionality Reduction PCA, Effect of dimensionality reduction
  • Eigenvalues, Linear transformations, DR preprocess, project of DR, DR illustration, coordinate transformation
  • Managing information loss, coponent split, ScreePlot, face recognition, Singular value Decomposition, SVD works
  • Mathematical form of SVD, SVD DR, Reconstruction of noisy image, Reconstruction graph, Recommendation systems
  • Content based filtering, Cosine similarity, recommendation function, collaborative filtering itembased and model based
  • Estimating missing values, Estimate error, SVM, classification boundary, Goal of SVM, Maximum margin
  • Support Vectors, mathematical analysis, margin, optimisation function, Soft margin, constraints and margin
  • conditions for finding margin, Deduce from equations, Hyper plane, Kernel Trick, Mapping to Higher Dimensional plane
  • Kernel calculation, applying higher dimensional space, Kernel functions, Sequential Minimal optimisation, classifying characters use case
  • Recognise handwritten letters, SVM Regression, SVM classes