Hasnat-Aarif-Aslam

All-Feature-Selection-Techniques-Filter-Wrapper-

Automatic-skewness-transformation

Python function to automatically transform skewed data in Pandas DataFrames

Convolutional-Neural-Network-CNN-

Customer-Churn-Prediction-using-Neural-Network-Binary-Classification

In this repository, I have created a simple neural network to teach beginners using the credit card customer churn prediction dataset from Kaggle. The workflow is intentionally kept simple, without any preprocessing, to highlight how to build and train a neural network.

Dimensionality-Reduction-Using-PCA

PCA on Digit Recognizer dataset from Kaggle to reduce its dimensionality

Encoding-Categorical-Data-Ordinal-Encoding-Label-Encoding

Exponentially-Weighted-Moving-Average-or-Exponential-Weighted-Average-EWMA

Fashion-MNIST-Classification-Using-ANN

Feature-Selection-Techniques

How-to-Improve-the-Performance-of-a-Neural-Network

This pdf shows some methods to fine tune the hyperparameters of a Neural Network to increase it's performance. It also puts light on some of the common problems related to Neural Networks along with their solutions.

Hasnat-Aarif-Aslam/How-to-Improve-the-Performance-of-a-Neural-Network

This pdf shows some methods to fine tune the hyperparameters of a Neural Network to increase it's performance. It also puts light on some of the common problems related to Neural Networks along with their solutions.

Hasnat-Aarif-Aslam/All-Feature-Selection-Techniques-Filter-Wrapper-

Hasnat-Aarif-Aslam/Automatic-skewness-transformation

Python function to automatically transform skewed data in Pandas DataFrames

Hasnat-Aarif-Aslam/Convolutional-Neural-Network-CNN-

Hasnat-Aarif-Aslam/Customer-Churn-Prediction-using-Neural-Network-Binary-Classification

In this repository, I have created a simple neural network to teach beginners using the credit card customer churn prediction dataset from Kaggle. The workflow is intentionally kept simple, without any preprocessing, to highlight how to build and train a neural network.

Hasnat-Aarif-Aslam/Dimensionality-Reduction-Using-PCA

PCA on Digit Recognizer dataset from Kaggle to reduce its dimensionality

Hasnat-Aarif-Aslam/Encoding-Categorical-Data-Ordinal-Encoding-Label-Encoding

Hasnat-Aarif-Aslam/Exponentially-Weighted-Moving-Average-or-Exponential-Weighted-Average-EWMA

Hasnat-Aarif-Aslam/Fashion-MNIST-Classification-Using-ANN

Hasnat-Aarif-Aslam/Feature-Selection-Techniques

Hasnat-Aarif-Aslam/Feature_Scaling_-_Distribution_Transformation

Hasnat-Aarif-Aslam/Graduates_Admission_Prediction_Using_ANN

This repository demonstrates a TensorFlow/Keras model for predicting graduate admission chances. It covers data loading, preprocessing (MinMax scaling), model creation, training, and evaluation. Furthermore, it includes visualizations of training/validation loss over epochs and computes the R² score for predictions.

Hasnat-Aarif-Aslam/Hand-Written-Digit-Classification-MNIST-Multi-Class-Classification

This repository demonstrates a TensorFlow/Keras model for classifying MNIST handwritten digits. It covers data loading, normalization, model creation, training with early stopping, and evaluation. Includes visualizations of loss and accuracy over epochs and explains image shape considerations for predictions.

Hasnat-Aarif-Aslam/Hasnat-Aarif-Aslam

Config files for my GitHub profile.

Hasnat-Aarif-Aslam/How-To-Handle-Time-Series-Date-Time-Features

Hasnat-Aarif-Aslam/How-to-train-a-model-on-immense-dataset-using-vaex-out-of-core-learning

Training a model on immense datasets using Vaex involves out-of-core learning, allowing data to be processed in memory-friendly chunks. Vaex efficiently handles, visualizes, and computes large dataframes, making it ideal for big data without needing to load the entire dataset at once. This ensures efficient and scalable model training.

Hasnat-Aarif-Aslam/KMeans-Hierarchical-and-DBSCAN

In this notebook, i have tried to appy KMeans, Hierarchical and DBSCAN clustering along PCA. The dataset used is Mall_Customers. In DBSCAN, certain type of Heatmaps are used to find the Epsilon and min_samples value which have performed quite well in identifying the correct number of clusters.

Hasnat-Aarif-Aslam/Pipelining-How-to-Create-Pipelines-in-Machine-Learning

Pipeline creation using Pipeline and make_pipeline along with ColumnTransformer and an Estimator

Hasnat-Aarif-Aslam/RNN-Recurrent-Neural-Network

Hasnat-Aarif-Aslam/Select_the_right_Threshold_value_using_ROC_Curve_for_binary_classification

Hasnat-Aarif-Aslam/Select_the_Right_Threshold_values_using_ROC_Curve

Hasnat-Aarif-Aslam/Time-Series

Hasnat-Aarif-Aslam/Vanishing-Gradient-Problem-With-Solution

This repository is based on the discussion about the Vanishing Gradient Problem. It explains some of the causes of this issue and provides solutions to help mitigate it.