No abstract

Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch learning setting, which requires the entire training data to be made available prior to the learning task. This is not scalable for many real-world scenarios where new data arrives sequentially in a stream form. We aim to address an open challenge of "Online Deep Learning" (ODL) for learning DNNs on the fly in an online setting. Unlike traditional online learning that often optimizes some convex objective function with respect to a shallow model (e.g., a linear/kernel-based hypothesis), ODL is significantly more challenging since the optimization of the DNN objective function is non-convex, and regular backpropagation does not work well in practice, especially for online learning settings. In this paper, we present a new online deep learning framework that attempts to tackle the challenges by learning DNN models of adaptive depth from a sequence of training data in an online learning setting. In particular, we propose a novel Hedge Backpropagation (HBP) method for online updating the parameters of DNN effectively, and validate the efficacy of our method on large-scale data sets, including both stationary and concept drifting scenarios.

In the cytoplasm of virtually all clear-cell renal cell carcinoma (ccRCC), speckle-type POZ protein (SPOP) is overexpressed and misallocated, which may induce proliferation and promote kidney tumorigenesis. In normal cells, however, SPOP is located in the nucleus and induces apoptosis. Here we show that a structure-based design and subsequent hit optimization yield small molecules that can inhibit the SPOP-substrate protein interaction and can suppress oncogenic SPOP-signaling pathways. These inhibitors kill human ccRCC cells that are dependent on oncogenic cytoplasmic SPOP. Notably, these inhibitors minimally affect the viability of other cells in which SPOP is not accumulated in the cytoplasm. Our findings validate the SPOP-substrate protein interaction as an attractive target specific to ccRCC that may yield novel drug discovery efforts.

No abstract