Large language models and prompt engineering basics - SkilBrill

Data Science Training Large language models and prompt engineering basics

Data Science Training

0% Completed

Module 1 — Data Science Foundations and Statistics

Data science lifecycle and problem framing

Descriptive and inferential statistics

Probability distributions and hypothesis testing

Experimental design and A/B testing

Data types, sampling, and bias handling

Module 2 — Python for Data Science

Python essentials: NumPy

Data manipulation, cleaning, and transformation

Visualization with Seaborn and Plotly

Working with databases and APIs

Jupyter notebooks and reproducible research

Module 3 — Machine Learning Fundamentals

Supervised vs unsupervised vs reinforcement learning

Train-test split, cross-validation, and overfitting

Feature engineering and selection

Model evaluation metrics: accuracy, precision, recall

Bias-variance tradeoff and model complexity

Module 4 — Supervised Learning Algorithms

Linear and logistic regression

Decision trees, random forests, and gradient boosting

Support Vector Machines and k-NN

Naive Bayes and ensemble methods

Hyperparameter tuning and model selection

Module 5 — Unsupervised Learning and Dimensionality Reduction

Clustering: K-means, hierarchical

Dimensionality reduction: PCA, t-SNE

Association rules and recommendation systems

Anomaly detection techniques

Evaluating clustering quality

Module 6 — Deep Learning and Neural Networks

Neural network fundamentals and backpropagation

Activation functions, optimizers, and regularization

Convolutional Neural Networks for image data

Recurrent Neural Networks and LSTMs for sequences

Introduction to Transformers and pre-trained models

Module 7 — Natural Language Processing

Text preprocessing and tokenization

TF-IDF, and word embeddings

Sentiment analysis and text classification

Named Entity Recognition and topic modeling

Large language models and prompt engineering basics

Module 8 — MLOps and Model Deployment

ML experiment tracking with MLflow

Model versioning, packaging, and registry

Deploying models as REST APIs

CI/CD for machine learning

Monitoring model drift and performance

Module 9 — Big Data Tools for Data Science

Spark for data science with PySpark

Distributed computing concepts

Working with cloud notebooks and GPU instances

Feature stores introduction

Scalable ML pipelines

Module 10 — Data Science in Production

Building end-to-end data science projects

Data ethics, privacy, and fairness

Storytelling with data and executive presentations

A/B testing and causal inference in production

Building a data science portfolio

Module 11 — Advanced Topics and Specializations

Time series forecasting: ARIMA

Computer vision applications

Recommender systems at scale

Graph analytics and network science

Generative AI and LLM fine-tuning overview

Module 12 — Interview Preparation and Career Development

Data science interview question bank

Case studies and take-home assignments

Statistics and coding rounds preparation

LinkedIn, and GitHub optimization

Mock interviews and salary negotiation

Announcements Course Info