-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
American grades, webpage, presentation months
* adjust grades to GPA * link webpage instead of github * add paper abstracts * add presentation months
- Loading branch information
Showing
6 changed files
with
55 additions
and
30 deletions.
There are no files selected for viewing
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,24 +1,46 @@ | ||
| @article{recurrency_occlusion, | ||
| author = "Hanlin Tang* and Bill Lotter* and Martin Schrimpf* and Ana Paredes and Josue Ortega Caro and Walter Hardesty and David Cox and Gabriel Kreiman", | ||
| title = "Recurrent computations for pattern completion", | ||
| journal = "submitted to Nature Neuroscience", | ||
| journal = "under review", | ||
| pubtype = "", | ||
| year = "2016", | ||
| abstract = "Making inferences from partial information constitutes a critical aspect of cognition. In visual perception, pattern completion leads to recognition of poorly visible or occluded objects. We combined psychophysics, physiology and computational models to test the hypothesis that pattern completion is implemented by recurrent computations. First, human subjects robustly recognized objects even when rendered <10% visible, but performance deteriorated when recurrent computations were interrupted by backward masking. Second, invasive physiological responses along the human ventral cortex also exhibited pattern completion, where responses to partially visible objects were delayed compared to whole objects, suggesting the need for additional computations. These physiological delays were correlated with the backward masking effects. Third, state-of-the-art feed-forward computational architectures were not robust to partial visibility. However, a model augmented with attractor-based recurrent connectivity matched human performance. These results provide a strong argument of plausibility for the role of recurrent computations in making visual inferences from partial information." | ||
| } | ||
|
|
||
| @article{should_i_use_tensorflow, | ||
| @manual{should_i_use_tensorflow, | ||
| author = "Martin Schrimpf", | ||
| title = "Should I use Tensorflow", | ||
| journal = "submitted", | ||
| note = "Seminar Paper", | ||
| organization = "University of Augsburg", | ||
| year = "2016", | ||
| } | ||
| archivePrefix = "arXiv", | ||
| eprint = {TODO}, | ||
| eprint = {1611.08903}, | ||
| primaryClass = "cs.AI", | ||
| url = "https://arxiv.org/abs/1611.08903", | ||
| abstract = "Google's Machine Learning framework TensorFlow was open-sourced in November 2015 and has since built a growing community around it. TensorFlow is supposed to be flexible for research purposes while also allowing its models to be deployed productively. This work is aimed towards people with experience in Machine Learning considering whether they should use TensorFlow in their environment. Several aspects of the framework important for such a decision are examined, such as the heterogenity, extensibility and its computation graph. A pure Python implementation of linear classification is compared with an implementation utilizing TensorFlow. I also contrast TensorFlow to other popular frameworks with respect to modeling capability, deployment and performance and give a brief description of the current adaption of the framework." | ||
| } | ||
|
|
||
| @MastersThesis{bachelors_thesis, | ||
| type = "Bachelor's Thesis", | ||
| author = "Martin Schrimpf", | ||
| title = "Scalable Database Concurrency Control using Transactional Memory", | ||
| school = "Technical University Munich", | ||
| year = "2014", | ||
| url = "http://mschrimpf.com/wp-content/uploads/2016/11/Scalable-Database-Concurrency-Control-using-Transactional-Memory-Martin-Schrimpf-TextSigned.pdf", | ||
| abstract = "Intel recently made available the optimistic synchronization technique Hardware Transactional | ||
| Memory (HTM) in their mainstream Haswell processor microarchitecture. | ||
| The first part of this work evaluates the core performance characteristics of the two programming | ||
| interfaces within Intel’s Transactional Synchronization Extensions (TSX), Hardware Lock Elision | ||
| (HLE) and Restricted Transactional Memory (RTM). Therein, a scope of application is defined | ||
| regarding inter alia the transaction size which is limited to the L1 DCache or even less with wrongly | ||
| aligned data due to cache associativity, the transaction duration restricted by Hardware interrupts | ||
| and a limit to the nesting of transactions. By comparing common data structures and analyzing | ||
| the behavior of HTM using hardware counters, the Hashmap is identified as a suitable structure | ||
| with a 134% speedup compared to classical POSIX mutexes. | ||
| In the second part, several latching mechanisms of MySQL InnoDB’s Concurrency Control are | ||
| selected and modified with different implementations of HTM to achieve increased scalability. We | ||
| find that it does not suffice to apply HTM naively to all mutex calls by using either HLE prefixes or | ||
| an HTM-enabled glibc. Furthermore, many transactional cycles often come at the price of frequent | ||
| aborted cycles which inhibits performance increases when measuring MySQL with the tx-bench | ||
| and too many aborts can even decrease the throughput to 29% of the unmodified version." | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters