Content: Classification, Sigmoid function, Decision Boundary, Cost function, Gradient descent, Overfitting, Regularisation

implements 8 deep learning models for handwritten digit classification using the MNIST dataset, with variations in architecture and activation functions.

Implementations of neural networks in python for the classification of MNIST datasets.

Predict whether the cancer is benign or malignant using logistic regression model.

Implementation Neural Network in C++

Predict number of JIRA bugs in SSD engineering dev process as a proxy for market readiness

Backpropagation in neural networks

Advance Deep learning with Model Implementation ANN && CNN (working.....)

trying out neural network with classic MNIST data set

This project utilizes a CNN model to classify cat and dog images through training and testing processes. The model is created using the Keras library on the TensorFlow backend.

This program implements logistic regression from scratch using the gradient descent algorithm in Python to predict whether customers will purchase a new car based on their age and salary.

Learn the fundamentals of building an Artificial Intelligence (AI) powered Neural Network using Python in this comprehensive tutorial. Discover the step-by-step process of designing, training, and fine-tuning a neural network to make accurate predictions on various data sets.Master the essential concepts of deep learning and unleash the power of AI

Deep Learning with TensorFlow Keras and PyTorch

This project provided practice with logistic regression and the cost functions MSE and log loss

유전알고리즘과 인공신경망을 활용허여 마리오 학습

Classification Techniques

Activation Function which used in neural network

Neural Networks from scratch (Inspired by Michael Nielsen book: Neural Nets and Deep Learning)

Avoiding the vanishing gradients problem by adding random noise and batch normalization

Machine Learning Model Using Logistic Regression with real dataset