Python3 Deep Dive

Dr. Fred Baptiste

Four part course covering the inner mechanisms and more complicated aspects of Python3.

1. Functional Programming | Variables, Functions, Closures, Decorators, Modules and Packages.
2. Iterators and Generators | Sequence Types, Iterables and Iterators, Generators, Iteration Tools, Context Managers.
3. Dictionaries, Sets and JSON | Dictionaries, Sets, Serialization and Deserialization, Specialized Dictionaries.
4. Object Oriented Programming | Classes, Polymorphism, Special Methods, Single Inheritance, Descriptors, Enumerations, Metaprogramming.

Scientific Computing with Python

freeCodeCamp | certification

Object Oriented Programming in Python. Completion of five projects. A link to each project is included with the certification link.

Data Analysis with Python

freeCodeCamp | certification

Data Analysis with Python, Pandas and Numpy. Completion of five projects. A link to each project is included with the certification link.

Understanding and Visualizing Data with Python

University of Michigan | certification

Data analysis and Visutalization in Python using Pandas, Matplotlib. Statistical theory and analytic techniques for probability and non-probability samples.

Course 1 of 3 of the Statistics with Python Specialization (in progress)

Machine Learning Specialization

Stanford University, DeepLearning.ai | certification

Three courses specialization introducing the theory and practice of machine learning.

1. Supervised Machine Learning | Regression and Classification. Machine learning models in Python using NumPy and scikit-learn. Supervised machine learning models for prediction and binary classification tasks, including linear regression and logistic regression.
2. Advanced Learning Algorithms | Neural Network with Tensorflow for multi-class classification. Machine learning best practices. Decision tree models.
3. Unsupervised Learning, Recommenders, Reinforcement Learning | Unsupervised learning techniques including clustering and anomaly detection. Recommender systems with collaborative filtering and content-based deep learning. Reinforcement Learning.

Deep Learning Specialization

deeplearning.ai | certification

Five courses specialization in the theory and practice of neural networks.

1. Neural Networks and Deep Learning | Foundational concept of neural networks and deep learning. Implementation of neural networks, key parameters in a neural network's architecture.
2. Improving Deep Neural Networks | Hyperparameter Tuning, Regularization and Optimization.
3. Structuring Machine Learning Projects | Building successful machine learning project. Error diagnosis, understanding complex ML settings, assessing performance, transfer learning, multi-task learning.
4. Convolutional Neural Networks | Applications of computer vision. Building different variations of convolutional networks to apply to visual detection, recognition and neural style transfer.
5. Sequence Models | Application of sequence models to natural language processing and more. Building Recurrent Neural Networks and commonly used variants such as GRUs and LSTMs.

Natural Language Processing Specialization

deeplearning.ai | certification

Four course certification covering the theory and practice of natural language processing.

1. NLP with Classification and Vector Spaces | Logistic regression, naive Bayes and word vectors to implement sentiment analysis, complete analogies and translate words.
2. NLP with Probabilistic Models | Dynamic programming, hidden Markov models and word embeddings to implement autocorrect, autocomplete and identify part-of-speech tags.
3. NLP with Sequence Models | LSTMs, GRUs and Siamese networks for sentiment analysis, text generation and named entity recognition.
4. NLP with Attention Models | Encoder-decoder, casual and self-attention to translate complete sentences, summarize text and build chatbots.

MLOps

Manifold AI Learning

Overview of various tools used in MLOps including Docker (packaging), MLFlow (experiment tracking), WhyLogs (monitoring ML systems)

Feature Engineering

Train in Data

Variable imputation, variable encoding, feature transformation, discretization, feature scaling, feature engineering pipeline.

Intro to AI Safety

Safe.ai / freeCodeCamp

Adversarial Robustness, Transparency, Anomaly Detection, Machine Ethics, Existential Risk.

LLM Engineering

Udemy

Building applications using LLM models, both closed and open

Gradio, HuggingFace, Langchain

Retrieval Augmented Generation (RAG)

Fine-tuning LLMs