Experiments

DeepMind internship project: Pinata - agent gets a reward if it touches the heaviest object

This is an extended work of "Which is heavier?" experiment from Learning to Perform Physics Experiments via Deep Reinforcement Learning (Denil et al. ICLR 2017).
Object densities are shown at the bottom right.

Agent trained with 15-second episodes. Agent trained with 50-second episodes
(time ticks 3 times faster, hence the video length 16 seconds)

GRAM Visualization

2D plot of disease representations learned from domain knowledge, initialized with GloVe
2D plot of disease representations learned from domain knowledge
2D plot of disease representations learned from fake domain knowledge
2D plot of disease representations learned by GRU, initialized with GloVe vectors
2D plot of disease representations learned by GRU, randomly initialized
2D plot of disease representations learned by GloVe
2D plot of disease representations learned by Skip-gram

Healthcare Concept Representation Learned by Med2Vec

codeEmb.npy: Embedding matrix of medical concepts (Python Numpy).
int2str.p: Mapping between integer code to string code (Python dictionary).
str2desc.p: Mapping between string code to descriptions (Python dictionary).

The embedding matrix codeEmb.npy has the shape 27523 by 200. Each row is a specific medical concept (diagnosis code, medication code or procedure code) represented by a 200 dimensional vector. int2str.p is a Python dictionary that maps the dimension number of the embedding matrix to the string code of the medical concept. For example the first dimension of codeEmb.npy can be mapped to a string code "D_401.9". The first letter of the string code could be D, R, or P which respectively stand for diagnosis, medication and procedure. str2desc.p is a Python dictionary that maps the string code to the actual description of the medical concept. For example, the string code "D_401.9" is mapped to the string description "Unspecified essential hypertension".

Healthcare Concept Representation Learning Visualization

2D plot of disease representations learned from non-negative Skip-gram

Disease network analysis from ICDM 2015

Disease network constructed from MIMIC II dataset