Learning a measure of similarity between pairs of objects is an important generic problem in machine learning. It is particularly useful in large scale applications like searching for an image that is similar to a given image or finding videos that are relevant to a given video. In these tasks, users look for objects that are not only visually similar but also semantically related to a given object. Unfortunately, the approaches that exist today for learning such semantic similarity do not scale to large datasets. This is both because typically their CPU and storage requirements grow quadratically with the sample size, and because many methods impose complex positivity constraints on the space of learned similarity functions.The current paper presents OASIS, an Online Algorithm for Scalable Image Similarity learning that learns a bilinear similarity measure over sparse representations. OASIS is an online dual approach using the passive-aggressive family of learning algorithms with a large margin criterion and an efficient hinge loss cost. Our experiments show that OASIS is both fast and accurate at a wide range of scales: for a dataset with thousands of images, it achieves better results than existing state-of-the-art methods, while being an order of magnitude faster. For large, web scale, datasets, OASIS can be trained on more than two million images from 150K text queries within 3 days on a single CPU. On this large scale dataset, human evaluations showed that 35% of the ten nearest neighbors of a given test image, as found by OASIS, were semantically relevant to that image. This suggests that query independent similarity could be accurately learned even for large scale datasets that could not be handled before.

Summary Reversible protein phosphorylation is a signaling mechanism involved in all cellular processes. To create a systems view of the signaling apparatus in budding yeast, we generated an E-MAP (epistatic miniarray profile) comprised of 100,000 pair-wise, quantitative genetic interactions, including virtually all protein kinases and phosphatases and key cellular regulators. Quantitative genetic interaction mapping reveals factors working in compensatory pathways (negative genetic interactions; e.g. synthetic lethality) or those operating in linear pathways (positive genetic interactions; e.g. suppression). Within kinases, phosphatases, and their substrates, we found an enrichment of positive genetic interactions. To develop a global view of the signaling apparatus, we isolated “triplet genetic motifs” and assembled these into a higher-order map. The resulting network view provides new insights into signaling pathway regulation, and revealed a link between the cell cycle kinase, Cak1, the Fus3 MAP kinase, and a pathway that regulates chromatin integrity during transcription by RNA polymerase II.

We present an approach to effectively use millions of images with noisy annotations in conjunction with a small subset of cleanly-annotated images to learn powerful image representations. One common approach to combine clean and noisy data is to first pre-train a network using the large noisy dataset and then fine-tune with the clean dataset. We show this approach does not fully leverage the information contained in the clean set. Thus, we demonstrate how to use the clean annotations to reduce the noise in the large dataset before fine-tuning the network using both the clean set and the full set with reduced noise. The approach comprises a multi-task network that jointly learns to clean noisy annotations and to accurately classify images. We evaluate our approach on the recently released Open Images dataset, containing ∼9 million images, multiple annotations per image and over 6000 unique classes. For the small clean set of annotations we use a quarter of the validation set with ∼40k images. Our results demonstrate that the proposed approach clearly outperforms direct fine-tuning across all major categories of classes in the Open Image dataset. Further, our approach is particularly effective for a large number of classes with wide range of noise in annotations (20-80% false positive annotations).

Electrophysiological mass potentials show complex spectral changes upon neuronal activation. However, it is unknown to what extent these complex band-limited changes are interrelated or, alternatively, reflect separate neuronal processes. To address this question, intracranial electrocorticograms (ECoG) responses were recorded in patients engaged in visuomotor tasks. We found that in the 10- to 100-Hz frequency range there was a significant reduction in the exponent χ of the 1/ fχ component of the spectrum associated with neuronal activation. In a minority of electrodes showing particularly high activations the exponent reduction was associated with specific band-limited power modulations: emergence of a high gamma (80–100 Hz) and a decrease in the alpha (9–12 Hz) peaks. Importantly, the peaks' height was correlated with the 1/ fχ exponent on activation. Control simulation ruled out the possibility that the change in 1/ fχ exponent was a consequence of the analysis procedure. These results reveal a new global, cross-frequency (10–100 Hz) neuronal process reflected in a significant reduction of the power spectrum slope of the ECoG signal.

Information processing by a sensory system is reflected in the changes in stimulus representation along its successive processing stages. We measured information content and stimulus-induced redundancy in the neural responses to a set of natural sounds in three successive stations of the auditory pathway-inferior colliculus (IC), auditory thalamus (MGB), and primary auditory cortex (A1). Information about stimulus identity was somewhat reduced in single A1 and MGB neurons relative to single IC neurons, when information is measured using spike counts, latency, or temporal spiking patterns. However, most of this difference was due to differences in firing rates. On the other hand, IC neurons were substantially more redundant than A1 and MGB neurons. IC redundancy was largely related to frequency selectivity. Redundancy reduction may be a generic organization principle of neural systems, allowing for easier readout of the identity of complex stimuli in A1 relative to IC.