Search

Quantifying similarity between neural representations -- e.g. hidden layer activation vectors -- is a perennial problem in deep learning and neuroscience research. Existing methods compare deterministic responses (e.g. artificial networks that lack stochastic layers) or averaged responses (e.g., trial-averaged firing rates in biological data). However, these measures of _deterministic_ representational similarity ignore the scale and geometric structure of noise, both of which play important roles in neural computation. To rectify this, we generalize previously proposed shape metrics (Williams et al. 2021) to quantify differences in _stochastic_ representations. These new distances satisfy the triangle inequality, and thus can be used as a rigorous basis for many supervised and unsupervised analyses. Leveraging this novel framework, we find that the stochastic geometries of neurobiological representations of oriented visual gratings and naturalistic scenes respectively resemble untrained and trained deep network representations. Further, we are able to more accurately predict certain network attributes (e.g. training hyperparameters) from its position in stochastic (versus deterministic) shape space., Comment: Published as a conference paper at ICLR 2023

Backround:Pancreatic ductal adenocarcinoma (PDAC) is the most common and deadly cancer. Surgical resection is the only possible cure for pancreatic cancer but often has a poor prognosis, and the role of adjuvant therapy is urgently explored.Methods:MicroRNAs (miRNAs) play very important role in tumorigenesis by regulating the target genes. In this study, we identified miR-320b lower-expressed in human pancreatic cancer tissues but relatively higher-expressed in the adjacent nontumor tissues.Results:Consistently，the expression of miR-320b in different pancreatic cancer cell lines was significantly lower than the normal pancreatic cells. In order to identify the effects of miR-320b on cell growth, we overexpressed miR-320b in PANC-1 and FG pancreatic cancer cell lines, CCK8 and BrdU incorporation assay results showed that miR-320b inhibited cell proliferation.Discussion:We next predicted miR-20b targeted FOXM1（Forkhead box protein M1）and identified the negative relationship between miR-320b and FOXM1.We also demonstrated that elevated miR-320b expression inhibited tumor growth in vivo.Conclusion:All of these results showed that miR-320b suppressed pancreatic cancer cells proliferation by targeting FOXM1, which might provide a new diagnostic marker for pancreatic cancer.

With the trend of adversarial attacks, researchers attempt to fool trained object detectors in 2D scenes. Among many of them, an intriguing new form of attack with potential real-world usage is to append adversarial patches (e.g. logos) to images. Nevertheless, much less have we known about adversarial attacks from 3D rendering views, which is essential for the attack to be persistently strong in the physical world. This paper presents a new 3D adversarial logo attack: we construct an arbitrary shape logo from a 2D texture image and map this image into a 3D adversarial logo via a texture mapping called logo transformation. The resulting 3D adversarial logo is then viewed as an adversarial texture enabling easy manipulation of its shape and position. This greatly extends the versatility of adversarial training for computer graphics synthesized imagery. Contrary to the traditional adversarial patch, this new form of attack is mapped into the 3D object world and back-propagates to the 2D image domain through differentiable rendering. In addition, and unlike existing adversarial patches, our new 3D adversarial logo is shown to fool state-of-the-art deep object detectors robustly under model rotations, leading to one step further for realistic attacks in the physical world. Our codes are available at https://github.com/TAMU-VITA/3D_Adversarial_Logo.