Home » Machine Learning

Useful resources for Machine Learning and Statistics.

• Home » Machine Learning
  • Specialization Certificates
  • References
    • General
    • Books
  • Projects
  • Useful Courses

Specialization Certificates

See Certifications for ML, DL, NLP, GANs, AI and MLops certificates.

References

General

• Interpretable Machine Learning: Guide for Making Black Box Models Explainable, Molnar, 2023
• Understanding Deep Learning, Prince, 2023
• The Little Book of Deep Learning, Fleuret, 2023
• Rules of Machine Learning: Best Practices for ML Engineering, Zinkevich, 2016
• Awesome Data Science

Books

• All of Statistics * A Concise Course in Statistical Inference, Wasserman, 2004
• Pattern Recognition and Machine Learning, Bishop, 2006
• The Elements of Statistical Learning, Hastie et al’s, 2009
• Machine Learning * A Probabilistic Perspective, Murphy, 2012
• An Introduction to Statistical Learning, James, Witten, Hastie & Tibshirani, 2013
• Deep Learning, Goodfellow, Bengio & Courville, 2016
• Mathematics for Machine Learning, Deisenroth, Faisal, Ong, 2020

Projects

A few projects I worked on:

• Predictive models and anomaly detection
  • Implementation of various models using classification algorithms, such as KNN, Decision Trees, Logistic Regression and SVM.
  • Elaboration of clustering algorithms for content-based and collaborative filtering recommender system.
  • Development of an Anomaly detection system using simple multivariate Gaussian.
• Music generation
  • Sequence model implementation of a Recurrent Neural Network to generate music using an LSTM network algorithm trained on a corpus of Jazz music.
• Speech recognition of a trigger word
  • Spectrogram analysis of audio recordings to make predictions from datasets.
  • Training of a trigger word detection model augmented with attention mechanism.
• Object detection and Face recognition
  • Implementation of a Convolutional Neural Network to detect various vehicles classes in pictures using the YOLO bounding-box model.
  • Face recognition using Convolutional Neural Network with triplet loss for fast performance.
• Sentiment analysis and Duplicate detection
  • Implementation of Natural Language Process to gauge sentiment using Siamese networks in a review platform.
  • Recognition of question duplicates using Siamese networks.
• Text summarization and Question answering
  • Implementation of Natural Language Processing Transformer architecture to create a tool that generates text summaries.
  • Implementation of a chatbot using transfer learning and models like T5, GPT and BERT to answer a given question.
• Art generation through style transfer and Generative Adversarial Network
  • Implementation of a Neural Style Transfer algorithm to generate novel artistic images, using a pretrained VGG-19 ConvNet.
  • Implementation of a tool using CycleGAN model to convert pictures of horses into zebras, and vice-versa.

Useful Courses

• Stanford University * Machine Learning by Andrew Ng
  • Logistic Regression, Regularization
  • Neural Networks
  • Advice for Applying Machine Learning, Machine Learning System Design
  • Support Vector Machines
  • Unsupervised Learning, Dimensionality Reduction
  • Anomaly Detection, Recommender Systems
  • Large Scale Machine Learning
• deeplearning.ai * Deep Learning Specialization by Andrew Ng
  • Neural Networks and Deep Learning
  • Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
  • Structuring Machine Learning Projects
  • Convolutional Neural Networks
  • Sequence Models
• Udacity * Deep Learning by Google
  • From Machine Learning to Deep Learning
  • Deep Neural Networks
  • Convolutional Neural Networks
  • Deep Models for Text and Sequences
• IBM * AI Engineering Professional Certificate by IBM
  • Machine Learning with Python
  • Scalable Machine Learning on Big Data using Apache Spark
  • Introduction to Deep Learning & Neural Networks with Keras
  • Deep Neural Networks with PyTorch
  • Building Deep Learning Models with TensorFlow
  • AI Capstone Project with Deep Learning
• deeplearning.ai * Natural Language Processing Specialization by Younes Bensouda Mourri and Łukasz Kaiser
  • Natural Language Processing with Classification and Vector Spaces
  • Natural Language Processing with Probabilistic Models
  • Natural Language Processing with Sequence Models
  • Natural Language Processing with Attention Models
• deeplearning.ai * Generative Adversarial Networks Specialization by Sharon Zhou
  • Build Basic Generative Adversarial Networks (GANs)
  • Build Better Generative Adversarial Networks (GANs)
  • Apply Generative Adversarial Networks (GANs)
• deeplearning.ai * Machine Learning Engineering for Production (MLOps) Specialization by Andrew Ng, Robert Crowe, Laurence Moroney
  • Introduction to Machine Learning in Production
  • Machine Learning Data Lifecycle in Production
  • Machine Learning Modeling Pipelines in Production
  • Deploying Machine Learning Models in Production
• deeplearning.ai * Generative AI with Large Language Models Specialization by Andrew Ng, Robert Crowe, Laurence Moroney
  • Generative AI use cases, project lifecycle, and model pre-training
  • Fine-tuning and evaluating large language models
  • Reinforcement learning and LLM-powered applications