Feature selection is an integral part of most learning algorithms. Due to the existence of irrelevant and redundant attributes, by selecting only the relevant attributes of the data, higher predictive accuracy can be expected from a machine learning method. In this paper, we propose the use of a three-layer feedforward neural network to select those input attributes that are most useful for dis...

We consider the following sparse signal recovery (or feature selection) problem: given a design matrix X ∈ Rn×m (m À n) and a noisy observation vector y ∈ R satisfying y = Xβ∗ + 2 where 2 is the noise vector following a Gaussian distribution N(0, σI), how to recover the signal (or parameter vector) β∗ when the signal is sparse? The Dantzig selector has been proposed for sparse signal recovery w...

Small interfering RNA (siRNA) is used in functional genomics applications to decrease the expression of a target gene, which may yield a biological effect that suggests a function for the target gene. The siRNA design tool scans a target gene for candidate siRNA sequences that satisfy user-adjustable rules. Selected candidates are then screened to identify those siRNA sequences that are specifi...

High-dimensional data in many areas such as computer vision and machine learning brings in computational and analytical difficulty. Feature selection which select a subset of features from original ones has been proven to be effective and efficient to deal with high-dimensional data. In this paper, we propose a novel AutoEncoder Feature Selector (AEFS) for unsupervised feature selection. AEFS i...

We describe an automated way to generate data for a practical LLVM instruction selector based on machine-generated description of the target architecture at register transfer level. The generated instruction selector can handle arbitrarily complex machine instructions with no internal control flow, and can automatically find and take advantage of arithmetic properties of an instructions, specia...

We discuss a new optimisation for recursive functions yielding multiple results in tuples for lazy functional languages, like Clean and Haskell. This optimisation improves the execution time of such functions and also reduces the amount of memory allocated in the heap by these functions, which reduces garbage collection costs. In some cases execution time is improved by more than a factor of tw...

The products of the Polycomb group of genes are cooperatively involved in repressing expression of homeotic selector genes outside of their appropriate anterior/posterior boundaries. Loss of maternal and/or zygotic function of Polycomb group genes results in the ectopic expression of both Antennapedia Complex and Bithorax Complex genes. The products of the trithorax group of genes are cooperati...

We introduce a new method — the group Dantzig selector — for high dimensional sparse regression with group structure, which has a convincing theory about why utilizing the group structure can be beneficial. Under a group restricted isometry condition, we obtain a significantly improved nonasymptotic `2-norm bound over the basis pursuit or the Dantzig selector which ignores the group structure. ...

We demonstrate a selector device with excellent performances (J MAX > 10 7 A/cm 2 , switching speed < 20ns) at the 30nm cell size. Furthermore, these promising device characteristics were achieved in a fully CMOS compatible stack (W/Ta 2 O 5 /TaO x /TiO 2 /TiN) with extremely thin oxide layer (< 10nm). Through the comprehensive understanding on the exponential I-V curve, the effect of intrinsic...