Source: Deep Learning on Medium
How to become a Pro in Machine Learning and Deep Learning Concepts
Here goes the learning path to become a pro in solving machine learning problems,
- Learn any programming language (Python is highly preferable)
- EDA concepts (2D plots, 3D plots, pair plots, PDF, CDF, univariate analysis, Mean, Median, Mode, variance, Std-var, Percentiles, Quantiles, Box plot, Violin plot, Multivariate analysis)
- Probability and statistics (Gaussian/Normal distribution, Symmetric distribution, Skewness and Kurtosis, Standard normal variate (z) and standardization, Kernel density estimation, Sampling distribution & Central Limit theorem, Q-Q Plot, Uniform Distribution, Bernoulli and Binomial distribution, Log-normal and power-law distribution, Co-variance, Pearson Correlation Coefficient, Spearman Rank Correlation Coefficient, Correlation vs Causation, Confidence Intervals, Hypothesis testing, Re-sampling and permutation test, K-S Test)
- Linear Algebra (Point/Vector (2-D, 3-D, n-D) , Dot product and the angle between 2 vectors, Projection, unit vector, Equation of a line (2-D), plane(3-D) and hyperplane (n-D) , Distance of a point from a plane/hyperplane, half-spaces, The equation of a circle (2-D), sphere (3-D) and hypersphere (n-D), Equation of an ellipse (2-D), ellipsoid (3-D) and hyper-ellipsoid (n-D), Square, Rectangle, Hyper-cube and Hyper-cubid)
- Dimensionality reduction (PCA & T-SNE)
- Miscellaneous Topics (Imbalanced vs balanced dataset, co-occurrence matrix, a similarity matrix, Train and test set differences, LOF, Normalization, Handling categorical and numerical features., Handling missing values by imputation, Curse of dimensionality, Bias-Variance tradeoff, Accuracy, Confusion matrix, TPR, FPR, FNR, TNR, Precision & recall, F1-score, Receiver Operating Characteristic Curve (ROC) curve and AUC, Log-loss, R-Squared/ Coefficient of determination, Median absolute deviation (MAD), Distribution of errors, Gradient descent, Learning rate, SGD algorithm, Feature engineering, Hyperparameter tuning, K-fold cross-validation)
- Machine learning( Supervised learning(KNN, SVM, Logistic Regression, Linear regression, Naive Bayes, Decision Trees, Ensemble Models) Unsupervised learning(K-Means, K-Means++, K-Medoids, Hierarchical clustering, DBSCAN, NMF, SVD))
- Deep Learning(Neural Networks, RNN, LSTMs, GANs, DCGANs, Transfer Learning and many more…)
- Practice in kaggle Knowledge competitions to get hands-on practice
These are the things you need to learn and do to become pro in machine learning.
If you have questions related to any concept comment below.