Restricted Boltzmann machines (RBMs) are often used as building blocks in greedy learning of deep networks. However, training this simple model can be laborious. Traditional learning algorithms often converge only with the right choice of metaparameters that specify, for example, learning rate scheduling and the scale of the initial weights. They are also sensitive to specific data representati...

This paper deals with the generation of balanced incomplete block designs (BIBD), a hard constrained combinatorial problem with multiple applications. This problem is here formulated as a combinatorial optimization problem (COP) whose solutions are binary matrices. Two different neighborhood structures are defined, based on bit-flipping and position-swapping. These are used within three metaheu...

In this paper, we demonstrate the ease in which an adaptive simulated annealing algorithm can be designed. Specifically, we use the adaptive annealing schedule known as the modified Lam schedule to apply simulated annealing to the weighted tardiness scheduling problem with sequence-dependent setups. The modified Lam annealing schedule adjusts the temperature to track the theoretical optimal rat...

This paper presents radix-4 and radix-8 Booth encoded modular multipliers over general Fp based on interleaved multiplication algorithm. An existing bit serial interleaved multiplication algorithm is modified using radix-4, radix-8 and Booth recoding techniques. The modified radix-4 and radix-8 versions of interleaved multiplication result in 50% and 75% reduction in required number of clock cy...

In this paper, the authors propose a new combined symmetric key cryptographic method, SJA-I, which basically has four steps: Firstly, each byte is broken into its equivalent binary format and then single bit manipulation is executed on that; secondly Modified Caesar Cipher technique (SD-REE) and TTJSA cipher algorithm are applied on the data (message) randomly, which depends on the key provided...

This paper proposes a random shifting data weighted averaging (RSDWA) algorithm where bidirectional circular shift register is co-worked with pseudo-random sequencer to form module, which makes mismatch error suppressed in the frequency domain, therefore it can achieve higher Spurious Free Dynamic Range (SFDR) compared traditional DWA. To verify proposed algorithm, 6-bit Nyquist-rate resistor l...

A kind of weighted Q-Learning algorithm suitable for control systems with continuous state and action spaces was proposed. The hidden layer of RBF network was designed dynamically by virtue of the proposed modified growing neural gas algorithm so as to realize the adaptive understanding of the continuous state space. Based on the standard Q-Learning implemented by RBF network, the weighted Q-Le...

In this paper we propose a modification of the 3-D Set Partitioning in Hierarchical Trees (3-D SPIHT) algorithm for very low bit-rate wavelet-based video coding. The modified algorithm, called 3-D Virtual SPIHT (3-D VSPIHT), virtually decomposes the coarsest level of the wavelet coefficients to reduce the number of three-dimensional (spatio-temporal) sets in the 3-D SPIHT algorithm. Our simulat...

In the field of image steganography research, more and attention is paid to importance stego robustness. order make accessible from laboratory practical applications, it becomes critical that images can resist JPEG compression transmission channel. this paper, an algorithm with strong robustness proposed. First, robust cover elements are selected using sign DCT coefficients which kept constant ...