Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Dynamic VAE Causal Discovery
This talk presents a VAE framework for learning dynamic causal relationships in multivariate time series by jointly modeling temporal dependencies and causal structure.
This talk introduces a novel framework for learning dynamic causal relationships in multivariate time series using a Variational Autoencoder (VAE) architecture. The model integrates recurrent and probabilistic components to jointly capture temporal dependencies and causal structure, addressing limitations of traditional Granger-causality and constraint-based approaches.
- PythonPython: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
- PyTorchPyTorch is the open-source machine learning framework: it provides a Python-first tensor library with strong GPU acceleration and a dynamic computation graph for building deep neural networks.PyTorch, developed by Meta AI, is a premier open-source deep learning framework favored in both research and production environments. Its core is a powerful tensor library (like NumPy) optimized for GPU acceleration, delivering 50x or greater speedups for complex computations. The key differentiator is its 'Pythonic' design and dynamic computation graph (eager execution), which allows for rapid prototyping and simplified debugging compared to static-graph frameworks. Leveraging its Autograd system for automatic differentiation, practitioners build and train models for computer vision and NLP; major companies like Tesla (Autopilot) and Microsoft utilize PyTorch for critical AI applications.
- NumPyNumPy is the fundamental Python package for high-performance scientific computing, centered on the powerful N-dimensional array object (ndarray).NumPy (Numerical Python) is the foundational library for scientific computing in Python, providing the core `ndarray` (N-dimensional array) object . This object is a homogeneous, fixed-size container that enables highly efficient, vectorized operations: often up to 50x faster than standard Python lists for large datasets . The library includes a comprehensive collection of routines for fast array manipulation, including linear algebra, Fourier transforms, and random simulation . Its performance advantage stems from its core being optimized C and C++ code , establishing it as the universal data structure for data exchange across the entire Python scientific computing ecosystem.
- SciPySciPy is the core open-source Python library for scientific computing: it provides high-level, efficient numerical routines built on NumPy arrays.SciPy is your essential toolbox for advanced scientific and technical computing in Python. It extends the NumPy foundation, offering specialized modules for critical tasks like optimization (`scipy.optimize`), numerical integration (`scipy.integrate`), linear algebra (`scipy.linalg`), and statistics (`scipy.stats`). The library wraps highly-optimized implementations (often C, C++, and Fortran) to ensure top-tier performance on complex problems. Use SciPy to solve differential equations, perform signal processing, or handle sparse matrices; it’s the proven, community-driven package for researchers and engineers globally.
- MatplotlibMatplotlib is the foundational Python library for generating static, animated, and interactive 2D and 3D data visualizations.This is the core Python visualization library: a comprehensive API for creating publication-quality figures. Matplotlib supports static, animated, and interactive plots across all platforms. It makes simple tasks (like a basic `plt.plot()`) easy, while enabling complex customizations: users control everything from visual style to layout. Figures export to multiple formats (e.g., PDF, PNG) and embed directly into environments like JupyterLab and various GUI toolkits.
Related projects
Building Community in Toronto
Toronto
Learn how a 300-person Toronto founder community was built, featuring an app using vector similarity and agentic web…
3D Traffic Twins with Video Generation with RAP
Toronto
Reconstruct messy traffic camera feeds into interactive 3D twins, infer flows, and generate "what-if" videos showing safer city…
DeepSeek-ing a Needle in a Haystack
Toronto
Learn how to use DeepSeek R1 agentic workflows and temporal prompting to filter, rank, and retrieve the most relevant…
Building FacultyFinder.io: An AI-Powered Academic Discovery Platform with Smart CV Matching
Toronto
Demoing an AI platform matching researcher CVs to Canadian faculty using web scraping, multi-LLM analysis, and PostgreSQL semantic…
AI and music - entertaining people's ears with AI
Toronto
Presenting efficient AI music generation via vocal-conditioned diffusion and showcasing a scalable karaoke app using various off-the-market AI…
Using AI for Force Multiplication
Toronto
See a technical deep dive into Control+S, an AI agent sandbox tool for evidence-first GRC analysis against frameworks…