Posts by Tags

Cognitive science

Interview about the Institute of Cognitive Science

1 minute read

Published:

I had a lot of fun working with the marketing team for the institute to explain the master’s program from the view of an international student. It is not apparent from a short clip, but there were many hours of raw footage required to produce each minute of video. I happened to be experimenting that day with mapping images to a Hilbert curve space to see if it improved classification of digits using a neural network.

Deep Learning

Deep Learning Video

less than 1 minute read

Published:

I had an opportunity to answer some questions about deep learning for Dagogo Altraide, aka ColdFusion’s latest video, “Why Deep Learning Now”, developed in collaboration with Intel.

Intel

LSTM

Linear algebra

Interview about the Institute of Cognitive Science

1 minute read

Published:

I had a lot of fun working with the marketing team for the institute to explain the master’s program from the view of an international student. It is not apparent from a short clip, but there were many hours of raw footage required to produce each minute of video. I happened to be experimenting that day with mapping images to a Hilbert curve space to see if it improved classification of digits using a neural network.

Mac OSX

Magenta

Math

Interview about the Institute of Cognitive Science

1 minute read

Published:

I had a lot of fun working with the marketing team for the institute to explain the master’s program from the view of an international student. It is not apparent from a short clip, but there were many hours of raw footage required to produce each minute of video. I happened to be experimenting that day with mapping images to a Hilbert curve space to see if it improved classification of digits using a neural network.

OpenCV

TensorFlow

High Performance Computing

less than 1 minute read

Published:

Optimizing deep learning model performance is computationally expensive, so I was pleased to discover that there are TensorFlow builds which are optimized for CPU systems (like my MacBook Pro). The benchmarks are impressive, and while this will likely not be the option for everyone, it is worth considering if your cloud setup is primarily using Xeon CPUs rather than GPUs.

deep learning

high performance computing

High Performance Computing

less than 1 minute read

Published:

Optimizing deep learning model performance is computationally expensive, so I was pleased to discover that there are TensorFlow builds which are optimized for CPU systems (like my MacBook Pro). The benchmarks are impressive, and while this will likely not be the option for everyone, it is worth considering if your cloud setup is primarily using Xeon CPUs rather than GPUs.

melody

optical flow

python