Yichuan Tang

A Large-Scale Model of the Functioning Brain

Modeling the Brain Neurons are pretty complicated cells. They display an endless variety of shapes that sprout highly variable numbers of axons and dendrites; they sport time- and voltage-dependent ion channels along with an impressive array of neurotransmitter receptors; and they connect intimately with near neighbors as well as former neighbors who have since moved away. Simulating a sizeable chunk of brain tissue has recently become achievable, thanks to advances in computer hardware and software. Eliasmith et al. (p. 1202; see the Perspective by Machens) present their million-neuron model of the brain and show that it can recognize numerals, remember lists of digits, and write down those lists—tasks that seem effortless for a human but that encompass the triad of perception, cognition, and behavior. Two-and-a-half million model neurons recognize images, learn via reinforcement, and display fluid intelligence. A central challenge for cognitive and systems neuroscience is to relate the incredibly complex behavior of animals to the equally complex activity of their brains. Recently described, large-scale neural models have not bridged this gap between neural activity and biological function. In this work, we present a 2.5-million-neuron model of the brain (called “Spaun”) that bridges this gap by exhibiting many different behaviors. The model is presented only with visual image sequences, and it draws all of its responses with a physically modeled arm. Although simplified, the model captures many aspects of neuroanatomy, neurophysiology, and psychological behavior, which we demonstrate via eight diverse tasks.

Challenges in Representation Learning: A Report on Three Machine Learning Contests

The ICML 2013 Workshop on Challenges in Representation Learning focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for organizers of future challenges and some comments on what kind of knowledge can be gained from machine learning competitions.

Robust Boltzmann Machines for recognition and denoising

While Boltzmann Machines have been successful at unsupervised learning and density modeling of images and speech data, they can be very sensitive to noise in the data. In this paper, we introduce a novel model, the Robust Boltzmann Machine (RoBM), which allows Boltzmann Machines to be robust to corruptions. In the domain of visual recognition, the RoBM is able to accurately deal with occlusions and noise by using multiplicative gating to induce a scale mixture of Gaussians over pixels. Image denoising and in-painting correspond to posterior inference in the RoBM. Our model is trained in an unsupervised fashion with unlabeled noisy data and can learn the spatial structure of the occluders. Compared to standard algorithms, the RoBM is significantly better at recognition and denoising on several face databases.

Challenges in representation learning

The ICML 2013 Workshop on Challenges in Representation Learning(1) focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for organizers of future challenges and some comments on what kind of knowledge can be gained from machine learning competitions.