A central repo for resources of all of our talks.
July 2016: Welcome to Danbury AI
Danbury AI is a public AI meetup group hosted by the Danbury Hackerspace that aims to stimulate discussion in the vast field of artificial intelligence and bring together locals that foster a passion for the field. We hold our in person meetings on the first Tuesday of every month at which we host a variety of presenters, discussions, and workshops. We maintain a lively web presence via slack so the conversation never stops.
- Slides - https://docs.google.com/presentation/d/18xtyqoZZpZCv15jmykcUx_iRhy6D7V8dbTeE8TUUgGk/edit?usp=sharing
Presented by: Andrew Riberio and Michael Rogowski
August 2016: Machine Learning with TensorFlow
TensorFlow™ is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API. TensorFlow was originally developed by researchers and engineers working on the Google Brain Team within Google's Machine Intelligence research organization for the purposes of conducting machine learning and deep neural networks research, but the system is general enough to be applicable in a wide variety of other domains as well.
- Slides - https://docs.google.com/presentation/d/1r9rdWVj0xYluiMjUDBP88dj8hMgA7LywqQXp6WtciGA/edit?usp=sharing
- Repo - https://github.com/DanburyAI/AUG2016-TensorFlow-Presentation-by-Andrew-Rib
Presented by: Andrew Riberio and Michael Rogowski
September 2016: Making 'ants' smarter (Fuzzy Logic + more)
An overview of distributed AI based on the society-of-agents paradigm leading to Fuzzy Logic as a mechanism to incorporate intelligence into an agent with limited computational resources. There will also be an overview and demo of Arduino One software running a simple simulated fuzzy thermostat.
- Slides and code - https://github.com/DanburyAI/SEP2016-Making-Ants-Smarter-by-Tom
Presented by: Tom Freund
October 2016: Generative vs. Discriminative Models
A model is a mathematical relation between one quantity and another. In Machine Learning and Data Science, these respective quantities are referred to as the “set of observations” and the “set of world states”. Discriminative models are constructed by specifying how “world states” depend on “observations”. Generative models, in contrast, are constructed by specifying how “observations” depend on “world states”. This talk explores the benefits, tradeoffs, and techniques of both modelling types.
Presented by: Michael Rogowski
November 2016: Introduction to Modeling Probability Distributions
Mike Rogowski's talk last month introduced probabilistic reasoning, and how we can infer the state of the world based on observations, using either discriminative models or generative models. This talk will dive deeper into how these models can be represented in practice. We'll cover topics from Chapters 3-7 of Simon Prince's book "Computer Vision: Models, Learning, and Inference" and the sample algorithms at computervisionmodels.com.
Presented by: Lambert Wixson
December 2016: Art and Machine Learning
Art has always been cherished as the most expressive and human production. The idea that a computer, a logical machine, can create the most quintessential human objects is preposterous to some. As anyone that has engaged in the artistic process will tell you, a lot of art is based on emotion, not logical rules. In this talk we will discuss the connectivist history leading to convolutional networks and their application in style transfer. I hope that the topics herein demonstrate to you that machine learning is a dramatic departure from rule based computing and that it does mimic intelligent behavior.
- Slides - https://docs.google.com/presentation/d/1hTMTsq32BQLZu4E4lCPNM0LuikFdNloswgquUfdphw0/edit?usp=sharing
Presented by: Andrew Ribeiro
Danbury AI is a public AI meetup group hosted by the Danbury Hackerspace that aims to stimulate discussion in the vast field of artificial intelligence and bring together locals that foster a passion for the field. We hold our in person meetings on the first Tuesday of every month at which we host a variety of presenters, discussions, and workshops. We maintain a lively web presence via slack so the conversation never stops.