This meetup was run by Peter Elger (fourTheorem) and Keelin Murphy (INFANT research center, UCC)
Cork AI meet-up 1 was the first meet-up sponsored by fourTheorem. The topic of discussion was an introduction to deep learning with a hands-on TensorFlow workshop. In this meet-up, fourTheorem’s Peter Elger spoke on the topic of TensorFlow and aided with tutorials. Co-host Keelin Murphy gave a talk on deep learning and convolutional neural networks. Video links from meetup can be found below.
This meet-up for Cork AI started with an introduction to deep-learning, how it differs from other machine-learning algorithms, and how it works. It then proceeded with a short introduction to TensorFlow (https://www.tensorflow.org/), and also provided a hands-on workshop implementing two TensorFlow tutorials.
- beer and pizza were provided to all attendees in order to help with workshop productivity!!
- We used Amazon Web Services (AWS) virtual machines to implement the tutorials, a full instruction was provided by Cork’s own AWS representative.
Footage from meet-up on Introduction to deep learning:https://www.youtube.com/watch?v=Lx6AEi7FWfU&t=1s
Footage from meet-up on Introduction to convolutional neural networks: https://www.youtube.com/watch?v=Zh59sv4SyLc&feature=youtu.be
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.
Footage from hands-on tutorial: https://www.youtube.com/watch?v=MfnFb4r5nWQ&t=1s
TensorFlow tutorials to recognize hand-written digits.