This post looks at composition. It starts with Lego. It then looks at a theory of why deep neural networks work and how they could be trained. It ends on how brains may embody these theories.
Composition
Sounds & Silence
What can we learn about the brain from the common patterns in human-generated audio?
Locality & Hierarchy
Locality. It constrains with ubiquity. But why are we unable to see it?
Looking at Cortical Column Function with Jeff Hawkins
Ever since "On Intelligence", I've been a Jeff Hawkins fanboy. It takes a lot of guts to invest all your wealth into understanding the brain. But what are his recent theories?
Easy Audio/Video Capture with Python
It's difficult to obtain audio/video data in Python. You just want a numpy array but how do you get this? This post presents a number of Python classes to address this issue.
Making Proper Histograms with Numpy and Matplotlib
How do you build proper histograms in Python?
Bio-Inspired Robotics for Beginners
Modern "deep" learning approaches have problems. The need for training data. A lack of robustness. Are they doing everything in reverse?
Capturing Live Audio and Video in Python
In my robotics projects I want to capture live audio and video data in Python. To save you several days, this blog post explains how I go about doing this.
Predicting the Future
The rise of machine learning and developments in neuroscience hint that prediction is key to how brains navigate the world. But how could this work in practice?
Playing Around with Retinal-Cortex Mappings
Here is a little notebook where I play around with converting images from a polar representation to a Cartesian representation. This is similar to the way our bodies map information from the retina onto the early visual areas. Mapping from the visual field (A) to the thalamus (B) to the cortex (C) These ideas are … Continue reading Playing Around with Retinal-Cortex Mappings
Robotic Ape 