I love to expand my knowledge through books and online classes. Recently, I completed the following courses on Coursera, DataCamp, and Linkedin Learning.
Data Science from Scratch
I have implemented the algorithms discussed in the book using Python. It includes the basics of linear algebra, statistics, and probability - and how they are used in data science. It includes the fundamentals of machine learning and the models that I implemented are k-nearest neighbors, Naïve Bayes, linear and logistic regression, decision trees, neural networks, clustering from scratch.
All codes are available on my Github. Click here.
I have implemented the algorithms discussed in the book using Python. It includes the basics of linear algebra, statistics, and probability - and how they are used in data science. It includes the fundamentals of machine learning and the models that I implemented are k-nearest neighbors, Naïve Bayes, linear and logistic regression, decision trees, neural networks, clustering from scratch.
All codes are available on my Github. Click here.
Courses on Coursera
IBM AI Engineering Professional Certificate
I completed all the courses of this professional certificate that includes fundamental concepts of machine learning and deep learning. ML algorithms including Classification, Regression, Clustering, and Dimensional Reduction were implemented using scipy & scikitlearn. Deep Learning models such as autoencoders, restricted Boltzmann machines, convolutional networks, recursive neural networks, and recurrent networks were built using Keras, PyTorch and Tensorflow libraries.
Machine Learning Codes | Deep Learning Codes | Certificate
I completed all the courses of this professional certificate that includes fundamental concepts of machine learning and deep learning. ML algorithms including Classification, Regression, Clustering, and Dimensional Reduction were implemented using scipy & scikitlearn. Deep Learning models such as autoencoders, restricted Boltzmann machines, convolutional networks, recursive neural networks, and recurrent networks were built using Keras, PyTorch and Tensorflow libraries.
Machine Learning Codes | Deep Learning Codes | Certificate
Machine Learning with Python
In this course I reviewed the theoretical concepts of machine learning such as regression, classification, clustering and recommender systems. I implemented the ML algorithms including decision trees, logistic regression, k-means, KNN, DBSCAN, SVM and hierarchical clustering in Python using Scikit-learn and Scipy.
Course Link | Codes | Certificate of Completion | IBM Badge
In this course I reviewed the theoretical concepts of machine learning such as regression, classification, clustering and recommender systems. I implemented the ML algorithms including decision trees, logistic regression, k-means, KNN, DBSCAN, SVM and hierarchical clustering in Python using Scikit-learn and Scipy.
Course Link | Codes | Certificate of Completion | IBM Badge
Deep Neural Networks with PyTorch
I started off with fundamentals such as Linear Regression, and logistic/softmax regression followed by feedforward deep neural networks with different activation functions, normalization and dropout layers. I used Python libraries including PyTorch to code Convolutional Neural Networks and several other Deep learning methods.
Course Link | Codes | Certificate of Completion | IBM Badge
I started off with fundamentals such as Linear Regression, and logistic/softmax regression followed by feedforward deep neural networks with different activation functions, normalization and dropout layers. I used Python libraries including PyTorch to code Convolutional Neural Networks and several other Deep learning methods.
Course Link | Codes | Certificate of Completion | IBM Badge
Introduction to Deep Learning & Neural Networks with Keras
In this course I used Keras library to build a neural network from scratch. I experimented with customized convolutional and pooling layers to solve the regression and MNIST classification problems using several deep convolutional neural network architectures.
Course Link | Codes | Certificate of Completion | IBM Badge
In this course I used Keras library to build a neural network from scratch. I experimented with customized convolutional and pooling layers to solve the regression and MNIST classification problems using several deep convolutional neural network architectures.
Course Link | Codes | Certificate of Completion | IBM Badge
Building Deep Learning Models with Tensorflow
In this course I used Tensorflow for curve fitting, regression, classification and minimization of error functions. I also trained different types of deep architectures, such as Convolutional Networks, Recurrent Networks and Autoencoders. Following training the CNN on MNIST dataset, I visualized the activation units in different convolutional layers.
Course Link | Codes | Certificate of Completion | IBM Badge
In this course I used Tensorflow for curve fitting, regression, classification and minimization of error functions. I also trained different types of deep architectures, such as Convolutional Networks, Recurrent Networks and Autoencoders. Following training the CNN on MNIST dataset, I visualized the activation units in different convolutional layers.
Course Link | Codes | Certificate of Completion | IBM Badge
AI Capstone Project with Deep Learning
In this capstone I trained deep learning frameworks using Pytorch library on real data provided by the course. The image data was first pre-processed and then pre-trained models were used to build the model and model validation.
Course Link | Codes | Certificate of Completion
In this capstone I trained deep learning frameworks using Pytorch library on real data provided by the course. The image data was first pre-processed and then pre-trained models were used to build the model and model validation.
Course Link | Codes | Certificate of Completion
Courses on Linkedin Learning and DataCamp
|
|
|
|
