We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates...

In this paper, we report the identification of a norCBQD gene cluster that encodes a functional nitric oxide reductase (Nor) in Nitrosomonas europaea. Disruption of the norB gene resulted in a strongly diminished nitric oxide (NO) consumption by cells and membrane protein fractions, which was restored by the introduction of an intact norCBQD gene cluster in trans. NorB-deficient cells produced ...

We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates...

A great deal of research has focused on algorithms for learning features from unlabeled data. Indeed, much progress has been made on benchmark datasets like NORB and CIFAR by employing increasingly complex unsupervised learning algorithms and deep models. In this paper, however, we show that several simple factors, such as the number of hidden nodes in the model, may be more important to achiev...

Aspergillus flavus is the main etiological agent for aflatoxin contamination of crops. Its close relative, A. oryzae, does not produce aflatoxins and has been widely used to produce fermented foods. We compared the phylogeny of A. oryzae isolates and L- and S-type sclerotial isolates of A. flavus using single nucleotide polymorphisms in the omtA gene in the aflatoxin biosynthesis gene cluster a...

The disposition of buprenorphine has been studied in two patient groups to assess the influence of impaired renal function on the metabolism of buprenorphine and two of its metabolites, buprenorphine-3-glucuronide (B3G) and norbuprenorphine (NorB). A single i.v. dose of 0.3 mg was given to 15 patients (nine with dialysis-dependent renal failure) undergoing lower abdominal or peripheral body sur...

We introduce a new type of top-level model for Deep Belief Nets and evaluate it on a 3D object recognition task. The top-level model is a third-order Boltzmann machine, trained using a hybrid algorithm that combines both generative and discriminative gradients. Performance is evaluated on the NORB database (normalized-uniform version), which contains stereo-pair images of objects under differen...

A common practice to gain invariant features in object recognition models is to aggregate multiple low-level features over a small neighborhood. However, the differences between those models makes a comparison of the properties of different aggregation functions hard. Our aim is to gain insight into different functions by directly comparing them on a fixed architecture for several common object...

Aflatoxins, the most toxic and carcinogenic family of fungal secondary metabolites, are frequent contaminants of foods intended for human consumption. Previous studies showed that formation of G-group aflatoxins (AFs) from O-methylsterigmatocystin (OMST) by certain Aspergillus species involves oxidation by the cytochrome P450 monooxygenases, OrdA (AflQ) and CypA (AflU). However, some of the ste...