# TensorBoard Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/tensorboard
> Markdown URL: https://aitinkerers.org/technologies/tensorboard.md
> Technology record last updated: 2026-03-24T15:18:18Z
> Generated: 2026-09-21T06:44:09Z

TensorBoard is the open-source visualization toolkit for machine learning: track experiment metrics, visualize model graphs, and debug training runs.

TensorBoard is your essential dashboard for ML workflow analysis, providing the measurements and visualizations needed to optimize models. It tracks key experiment metrics like loss and accuracy over time using the Scalars dashboard, helping you spot issues like overfitting immediately. You can visualize the complete model graph to understand data flow and debug architecture errors (e.g., with Keras models). Furthermore, it offers tools like the Histograms dashboard for examining weight and bias distributions, the Embedding Projector for dimensionality reduction (e.g., visualizing high-dimensional word embeddings), and full support across both the TensorFlow and PyTorch ecosystems.

- Official technology site: https://www.tensorflow.org/tensorboard/
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Building Interactive Worlds with VAEs and JEPA](https://toronto.aitinkerers.org/talks/rsvp_UL1Li1c7ki0)

I'm working on using VAEs and I-JEPA to generate worlds you can move through. The goal is to teach a model to both imagine and understand/predict how they change as you explore. I will show a custom VAE that generates novel scenes from GTA5 and a custom implementation of I-JEPA that's learning the world dynamics. The goal is to use them together to predict the next frame based on input. The VAE I'll show is custom and I will focus in on the loss calculation to show the reconstruction loss via the KL Divergence. I'll also show the outputs of the model with different latent dimensions (i.e. too big vs too small vs just right). For I-JEPA I'll compare and contrast it against the VAE and why it's different. I'll use a Notebook to illustrate how the algorithm works and 🤞a decoder to show how what it has learnt about the world.

- Event context: AI Tinkerers Toronto - June 2025 Meetup at NEXT Canada -- sponsored by Intel AI! — 2025-06-18 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_UL1Li1c7ki0

## Related Technologies

- [Lightning](https://aitinkerers.org/technologies/lightning) ([Markdown](https://aitinkerers.org/technologies/lightning.md)) — 1 public demo
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos