- JEDHA Bootcamp's Fullstack training course leads to official professional certification (RNCP 35_288): “Machine Learning Engineer”.
- The Fullstack training comes after the Essential training and before the Lead training :
- My Notes and Projects of the Essential training are available here
- My Notes and Projects of the Lead training are available here. JEDHA Bootcamp's Lead training course leads to official professional certification (RNCP 38_777): “Artificial intelligence architect”.
- 12 weeks
- march 18 - june 18 2024
- JEDHA web page of the Fullstack training
- Python Programming
- classes, git...
- Exploratory Data Analysis
- numpy
- pandas
- plotly
- Project : Speed Dating
- Data Collection and Management
- HTTP
- API
- Scraping
- AWS S3 Boto3
- AWS RDS SQLAlchemy
- Project : Kayak
- Big Data
- RDDs (Resilient Distributed Datasets)
- Databricks, Tidy, SparkSQL, pgAdmin
- Spark, PySpark
- AWS RedShift
- Project : Steam
- Supervised Machine Learning
- Sklearn
- Linear Regression
- Regularization and Hyperparamter optimization
- Logistic Regression
- Decision Tree, Random Forest
- SVM support vector machine
- Ensemble Learning AdaBoost XGBoost
- Model Selection et Evaluation
- Times Series
- Project : Walmart
- Project : Coversion Rate Challenge
- Unsupervised Machine Learning
- kMeans
- DBSCAN
- PCA
- NLP Natural Language Processing for unsupervised learning
- Topic Modeling
- Project : Uber
- Project : North Face
- Deep Learning
- Gradient Descent
- Neural Networks
- TensorFlow, Keras
- CNN Convolutiional Neural Network
- Transfer Learning
- GAN
- Word Embedding, Word2Vec
- RNN Recurrent Neural Network
- Encoder Decoder
- Attention
- Project : AT&T
- Deployment
- Local Dev
- Dashboard Streamlit
- Docker
- Deploy to Heroku
- MLFlow
- Package & Serve models
- API for your model
- Project : Getaround
- Career Coaching
- Final Project
- Project : Skin Project. I was in charge of the architecture and infra.
- Certification
This project was developed for personal and educational purposes. Feel free to explore and use it to enhance your own learning in machine learning.
Given the nature of the project, external contributions are not actively sought nor encouraged. However, constructive feedback aimed at improving the project (in terms of speed, accuracy, comprehensiveness, etc.) is welcome. Please note that this project was created as part of a certification process, and it is unlikely to be maintained after the final presentation.