Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEmbedding Projector: Interactive Visualization and Interpretation of Embeddings
105
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. Researchers and developers often need to explore the properties of a specific embedding, and one way to analyze embeddings is to visualize them. We present the Embedding Projector, a tool for interactive visualization and interpretation of embeddings.
rate research
Read More
This paper introduces Polyphorm, an interactive visualization and model fitting tool that provides a novel approach for investigating cosmological datasets. Through a fast computational simulation method inspired by the behavior of Physarum polycephalum, an unicellular slime mold organism that efficiently forages for nutrients, astrophysicists are able to extrapolate from sparse datasets, such as galaxy maps archived in the Sloan Digital Sky Survey, and then use these extrapolations to inform analyses of a wide range of other data, such as spectroscopic observations captured by the Hubble Space Telescope. Researchers can interactively update the simulation by adjusting model parameters, and then investigate the resulting visual output to form hypotheses about the data. We describe details of Polyphorms simulation model and its interaction and visualization modalities, and we evaluate Polyphorm through three scientific use cases that demonstrate the effectiveness of our approach.
Our goal is to enable machine learning systems to be trained interactively. This requires models that perform well and train quickly, without large amounts of hand-labeled data. We take a step forward in this direction by borrowing from weak supervision (WS), wherein models can be trained with noisy sources of signal instead of hand-labeled data. But WS relies on training downstream deep networks to extrapolate to unseen data points, which can take hours or days. Pre-trained embeddings can remove this requirement. We do not use the embeddings as features as in transfer learning (TL), which requires fine-tuning for high performance, but instead use them to define a distance function on the data and extend WS source votes to nearby points. Theoretically, we provide a series of results studying how performance scales with changes in source coverage, source accuracy, and the Lipschitzness of label distributions in the embedding space, and compare this rate to standard WS without extension and TL without fine-tuning. On six benchmark NLP and video tasks, our method outperforms WS without extension by 4.1 points, TL without fine-tuning by 12.8 points, and traditionally-supervised deep networks by 13.1 points, and comes within 0.7 points of state-of-the-art weakly-supervised deep networks-all while training in less than half a second.
We present a system that allows users to visualize complex human motion via 3D motion sculptures---a representation that conveys the 3D structure swept by a human body as it moves through space. Given an input video, our system computes the motion sculptures and provides a user interface for rendering it in different styles, including the options to insert the sculpture back into the original video, render it in a synthetic scene or physically print it. To provide this end-to-end workflow, we introduce an algorithm that estimates that humans 3D geometry over time from a set of 2D images and develop a 3D-aware image-based rendering approach that embeds the sculpture back into the scene. By automating the process, our system takes motion sculpture creation out of the realm of professional artists, and makes it applicable to a wide range of existing video material. By providing viewers with 3D information, motion sculptures reveal space-time motion information that is difficult to perceive with the naked eye, and allow viewers to interpret how different parts of the object interact over time. We validate the effectiveness of this approach with user studies, finding that our motion sculpture visualizations are significantly more informative about motion than existing stroboscopic and space-time visualization methods.
Background: It is possible to find many different visual representations of data values in visualizations, it is less common to see visual representations that include uncertainty, especially in visualizations intended for non-technical audiences. Objective: our aim is to rigorously define and evaluate the novel use of visual entropy as a measure of shape that allows us to construct an ordered scale of glyphs for use in representing both uncertainty and value in 2D and 3D environments. Method: We use sample entropy as a numerical measure of visual entropy to construct a set of glyphs using R and Blender which vary in their complexity. Results: A Bradley-Terry analysis of a pairwise comparison of the glyphs shows participants (n=19) ordered the glyphs as predicted by the visual entropy score (linear regression R2 >0.97, p<0.001). We also evaluate whether the glyphs can effectively represent uncertainty using a signal detection method, participants (n=15) were able to search for glyphs representing uncertainty with high sensitivity and low error rates. Conclusion: visual entropy is a novel cue for representing ordered data and provides a channel that allows the uncertainty of a measure to be presented alongside its mean value.
3D visualization is an important data analysis and knowledge discovery tool, however, interactive visualization of large 3D astronomical datasets poses a challenge for many existing data visualization packages. We present a solution to interactively visualize larger-than-memory 3D astronomical data cubes by utilizing a heterogeneous cluster of CPUs and GPUs. The system partitions the data volume into smaller sub-volumes that are distributed over the rendering workstations. A GPU-based ray casting volume rendering is performed to generate images for each sub-volume, which are composited to generate the whole volume output, and returned to the user. Datasets including the HI Parkes All Sky Survey (HIPASS - 12 GB) southern sky and the Galactic All Sky Survey (GASS - 26 GB) data cubes were used to demonstrate our frameworks performance. The framework can render the GASS data cube with a maximum render time < 0.3 second with 1024 x 1024 pixels output resolution using 3 rendering workstations and 8 GPUs. Our framework will scale to visualize larger datasets, even of Terabyte order, if proper hardware infrastructure is available.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
