Name: Constantine Mbufung
Type: User
Company: CM Media
Bio: Senior Data scientist with 6+ years of experience in project work, company work, and freelance jobs. Skilled in machine learning, Deep Learning, R, Python
Twitter: Constantine_N_M
Location: Douala Cameroun
Blog: https://cmmedia.cm
Constantine Mbufung's Projects
In 100 days i will an OCR invoice recognition software
First Steps with TensorFlow
Go from absolute beginner in Power BI to getting hired as a confident and effective Analyst. Learn Power BI (+ much more) by analyzing real-world datasets and building enterprise-level projects.
An online clinical codes repository to improve validity and reproducability of medical database research
Building a convolutional neural network with tensorflow to classify cats and dogs
building a convolutional neural network with tensorflow on the MNIST dataset
I will teach you step by step on to build machine learning model using pytorch
Config files for my GitHub profile.
# Data Analyis with Python Python is a great lanague for doing data analysis. Python have fantastic packages sucha s Pandas, Numpy and Matplotlib that give you a single place to analyse data and do visualization. We'll use Pandas to analyze data on video game reviews from IGN one of the most popular video review site. We are going to use Python 3.5 and google colab running jupyter notebook 4 # Import Data with Pandas our file is a csv file, comma-separated values
In this tutorial series, we will learn the basics of TensorFlow, neural networks and deep learning: We will learn: What is Tensorflow and keras An intriduction to neural networks what the perception and multi-perception are real world examples: handwritten digits recognition
A microframework based on Werkzeug, Jinja2 and good intentions
iDOTA is AI-based retinal screening application that is developed at the Douala School of AI Research Lab(DSAIRLab) to easily diagnose and prevent blindness in Cameroon. According to the WHO, the number of people of all ages visually impaired is estimated to be 285 million, of whom 39 million are blind. People 50 years and older are 82% of all blind. The major causes of visual impairment are uncorrected refractive errors (43%) and cataract (33%); the first cause of blindness is cataract (51%).
this is the first bootstrap 4 beta project
Random jupyter notebooks on data analysis and machine learning
Don't train deep learning models blindfolded! Be impatient and look at each epoch of your training! A live training loss plot in Jupyter Notebook for Keras, PyTorch and other frameworks. An open source Python package by Piotr Migdał et al. When used with Keras, Live Loss Plot is a simple callback function.
Applications of LSTM - Image caption Generation. For generating captions for images, we will use a popular dataset for image captioning tasks known as Microsoft Common Objects in Context (MS-COCO). We will �rst process images from the dataset (MS-COCO) to obtain an encoding of the images with a pretrained Convolutional Neural Network (CNN), which is already good at classifying images. The CNN will take a �xed-size image as the input and output the class the image belongs to (for example, cat, dog, bus, and tree). Using this CNN, we can obtain compressed encoded vectors describing images. Then we will process the captions of the images to learn the word embeddings of the words found in captions. We can also use pretrained word vectors for this task. Finally, having obtained both the image and word encodings, we will feed them into an LSTM and train it on the images and their respective captions.
Movie Reviews with Deep Learning Tensorflow
mysql insert country list into database
Lets implement a neural network that is able to classify digits. For this task, we will be using the famous MNIST dataset made available at http://yann.lecun.com/exdb/mnist/
A common problem across businesses in many industries is that of customer churn. Businesses often have to invest substantial amounts attracting new clients, so every time a client leaves it represents a significant investment lost. Both time and effort then need to be channelled into replacing them. Being able to predict when a client is likely to leave and offer them incentives to stay can offer huge savings to a business. This is the essence of customer churn prediction; how can we quantify if and when a customer is likely to churn?
Today i am starting a tutorial on using python for finance- we are going to pull stock data from yahoo finance and do data analysis and backtesting using zipline
Some applications about R Programmig Language
Mirror of Apache Spark
This is test for a new project
we going to used LSTM for text generation. Credit to Thushan Ganegedara. You can read his book on packt.com on NLP using Tensorflow
Titanic Data Analysis with python