Code&Data Insights

Vanishing Gradients - usually occurs due to the fact that some activation functions squash the input into small values result in small gradients that result in negligible updates to the weights of the model - Or sometimes the input values are small to begin with : When backpropagation the gradient through long chains of computations, the gradient gets smaller and smaller - causes the gradient of..

Regularization : prevent overfitting and improve the generalization of a model - It introduces additional constraints or penalties into the model training process to discourage the model from becoming too complex. - It aims to strike a balance between fitting the training data well and maintaining simplicity in the model Early Stopping : monitor the performance after each epoch on the validation..

Benefits of Advanced optimization methods - Faster Convergence - Improved Stability - Avoiding Local Minima - Better Generalization Momentum : accumulates an exponentially-decaying moving average of the past gradients - NOT ONLY denpends on learning rate, but ALSO past gradients (SDG with Batch) If the previous update vt is very different from the current gradient => little update If previous up..

Optimization - Training a machine learning model often requires solving Optimization problem => have to find the parameters of the function f that minimizes the loss function using the training data. Problem in Optimization in Multi dimensional Spaces - TOO MANY CRITICAL POINT! (critical points where f'(x) = 0) => local minima, maxima, and saddle points How to Solve Optimization Problem? Solutio..

Generalization : ability of a machine learning algorithm(model) to perform well on unseen data Training Loss : loss function, computed with training set Test Loss : loss function, computed with test set => More training set leads better generalization! Capacity : Underfittingand Overfittingare connected to the capacity of the model. capacity(= representational capacity) : attempts to quantify ho..

: the process of identifying and connecting records or data entries that correspond to the same real-world entity or individual in one or more data sources. - Improves data quality and integrity - Fosters re-use of existing data sources - Optimize space [ Atomic String Similarity ] Atomic String Similarity, why it is important? - Information Retrieval : similarity of string - Da..

[ Cohort Analysis ] Cohort analysis breaks the data in a data set into related groups before analysis. - a kind of behavior analytics - a group of subjects which share a defining feature and observing the behaviour of the group(cohort) over time and compare it to other cohorts. * Main Stages for Cohort Analysis 1) Determine what question you want to answer to improve business, product, user expe..

[ Connecting to & Preparing Data ] Q. How to reduce the size of an extract ? A1) Aggregate the data to visible dimension A2) Hide All Unsued field => When we create an extract, we get many size options We can choose only include a sample of the data, Or aggregate to visible dimensions Or use extract filters Or choose the physical table option instead of logical table Q. The best reason to use a ..