Rohan & Lenny #3: Recurrent Neural Networks & LSTMs

@tachyeonz : It seems like most of our posts on this blog start with “We’re back!”, so… you know the drill. It’s been a while since our last post — just over 5 months — but it certainly doesn’t feel that way.

Read More

Connect On:
Twitter :@tachyeonz

Phase-Functioned Neural Networks for Character Control

@tachyeonz : Created on April 30, 2017, 3:48 p.m. This year at SIGGRAPH I am presenting Phase-Functioned Neural Networks for Character Control. This paper uses a new kind of neural network called a “Phase-Functioned Neural Network” to create a character controller suitable for games.

Read More

Connect On:
Twitter :@tachyeonz

Have We Forgotten about Geometry in Computer Vision?

@tachyeonz : Deep learning has revolutionised computer vision. Today, there are not many problems where the best performing solution is not based on an end-to-end deep learning model. In particular, convolutional neural networks are popular as they tend to work fairly well out of the box.

Read More

Connect On:
Twitter :@tachyeonz

Vanilla Recurrent Neural Networks

@tachyeonz : Most tutorial, deep learning blog posts that introduce recurrent neural networks (RNNs) use Long Short Term Memory (LSTM) cells in their examples.  This happens because training vanilla recurrent neural networks is more difficult, and the results are less impressive.

Read More

Connect On:
Twitter :@tachyeonz

Personalized Aesthetics: Recording the Visual Mind using Machine Learning

@tachyeonz : Visual aesthetics are very personal, often subconscious, and hard to express.  In a world with an overload of photographic content, a lot of time and effort is spent manually curating photographs, and it’s often hard to separate the good images from the visual noise.

Read More

Connect On:
Twitter :@tachyeonz

Understanding The Limits Of Deep Learning

@tachyeonz : Artificial intelligence has reached peak hype. News outlets report that companies have replaced workers with IBM Watson and algorithms are beating doctors at diagnoses. New A.I. startups pop up every day and claim to solve all your personal and business problems with machine learning.

Read More

Connect On:
Twitter :@tachyeonz

Convolutional neural networks, Part 1

@tachyeonz : Having recovered somewhat from the last push on deep learning papers, it’s time this week to tackle the next batch of papers from the ‘top 100 awesome deep learning papers.

Read More

Connect On:
Twitter :@tachyeonz

Convolution neural nets, Part 2

@tachyeonz : This is a very nice study.

Read More

Connect On:
Twitter :@tachyeonz

Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning

@tachyeonz : Deep learning is a field with intense computational requirements and the choice of your GPU will fundamentally determine your deep learning experience.

Read More

Connect On:
Twitter :@tachyeonz

Can FPGAs Beat GPUs in Accelerating Next-Generation Deep Learning?

@tachyeonz : Continued exponential growth of digital data of images, videos, and speech from sources such as social media and the internet-of-things is driving the need for analytics to make that data understandable and actionable. Data analytics often rely on machine learning (ML) algorithms.

Read More

Connect On:
Twitter :@tachyeonz

Overcoming Catastrophic Forgetting in Neural Networks

@tachyeonz : I’ve found that the overwhelming majority of online information on artificial intelligence research falls into one of two categories: the first is aimed at explaining advances to lay audiences, and the second is aimed at explaining advances to other researchers.

Read More

Connect On:
Twitter :@tachyeonz

3 cool machine learning projects using TensorFlow and the Raspberry Pi

@tachyeonz : In early 2017, the Raspberry Pi Foundation announced a Google developer survey, which requested feedback from the maker community on what tools they wanted on the Raspberry Pi.

Read More

Connect On:
Twitter :@tachyeonz