Noman Javed

London School of Economics and Political Science | LSE · Department of Philosophy, Logic and Scientific Method

A common goal in cognitive science involves explaining/predicting human performance in experimental settings. This study proposes a single GEMS computational scientific discovery framework that automatically generates multiple models for verbal learning simulations. GEMS achieves this by combining simple and complex cognitive mechanisms with geneti...

A fundamental issue in cognitive science concerns the interaction of the cognitive "how" operations, the genetic/memetic "why" processes, and by what means this interaction results in constrained variability and individual differences. This study proposes a single GEVL model that combines complex cognitive mechanisms with a genetic programming appr...

How can we infer the strategies that human participants adopt to carry out a task? One possibility, which we present and discuss here, is to develop a large number of strategies that participants could have adopted, given a cognitive architecture and a set of possible operations. Subsequently, the (often many) strategies that best explain a dataset...

Genetic programming (GP), a widely used Evolutionary Computing technique, suffers from bloat -- the problem of excessive growth in individuals' sizes. As a result, its ability to efficiently explore complex search spaces reduces. The resulting solutions are less robust and generalisable. Moreover, it is difficult to understand and explain models wh...

Scientific discovery is a driving force for progress, involving creative problem-solving processes to further our understanding of the world. Historically, the process of scientific discovery has been intensive and time-consuming; however, advances in computational power and algorithms have provided an efficient route to make new discoveries. Compl...

The last decade has seen amazing performance improvements in deep learning. However, the black-box nature of this approach makes it difficult to provide explanations of the generated models. In some fields such as psychology and neuroscience, this limitation in explainability and interpretability is an important issue. Approaches such as genetic pr...

Stock market attracts many investors to earn money by investing timely. But stocks are very volatile and their non-linear behavior make them more unpredictable and it is humanly impossible to predict the stocks accurately. Neural networks based machine learning techniques can be employed for the said purpose. Since there are many types of neural ne...

Autonomous driving is one of the newly emerging feats in artificial intelligence (AI). The challenge in developing autonomous cars is to design controllers that can steer a vehicle in the right direction with enough speed. A good controller activates a set of multiple actuators simultaneously. The output of the controller is a function of the senso...

—Investors and researchers have continuously been trying to predict the behavior of the stock market. The accurate predictions can be helpful in taking timely and correct investment decisions. Many statistical and machine learning based techniques are proposed. Neural Networks are among the ones having the potential to model the nonlinear behavior...

In this paper, we propose a scheme for evolving multiple-input-multiple-output (MIMO) artificial neural networks (ANNs) using grammatical evolution (GE). GE is a well-known technique for program evolution. While it has also been used for the evolution of ANN structures in the past, little work is reported on the evolution of MIMO ANNs. MIMO ANNs ar...

Stock market attracts many investors to earn money by investing timely. But stocks are very volatile and their non-linear behavior make them more unpredictable and it is humanly impossible to predict the stocks accurately. Neural networks based machine learning techniques can be employed for the said purpose. Since there are many types of neural ne...

Finding optimum trading strategies that maximize profit has been a human desire since the inception of the first stock market. Many techniques have been employed ever since to accomplish this goal without sacrificing much computational power and time. In this paper, Genetic Algorithms (GAs) are used to achieve the aforementioned objectives. The per...

In this study, a new data embedding method is proposed to enhance the embedding payload by combining irreversible and reversible methods. The proposed method is based on pixel value difference (PVD), least significant bit (LSB) substitution, PVD shift, and modification of prediction error (MPE). A pixel block (2 × 1) is initially classified into lo...

The fundamental objectives of image steganographic algorithm are to simultaneously achieve high payload, good visual imperceptibility, and security. This paper proposes a new data hiding method that increases visual quality and payload, as well as maintains steganographic security. The proposed scheme consists of two novel methods of parity-bit pix...

The goal of image steganographic methods considers three main key issues: High embedding capacity, good visual symmetry/quality, and security. In this paper, a hybrid data hiding method combining the right-most digit replacement (RMDR) with an adaptive least significant bit (ALSB) is proposed to provide not only high embedding capacity but also mai...

Structured parallelism approaches are a trade-off between automatic parallelisation and concurrent and distributed programming such as Pthreads and MPI. Skeletal parallelism is one of the structured approaches. An algorithmic skeleton can be seen as higher-order function that captures a pattern of a parallel algorithm such as a pipeline, a parallel...

Orléans Skeleton Library (OSL) is a library of parallel algorithmic skeletons in C++ on top of MPI. It provides a structured approach to parallel programming. Skeletons in OSL are based on the bulk synchronous parallelism model. In this paper we present a formal semantics of OSL: its programming model formalised with the Coq proof assistant.

Orléans Skeleton Library (OSL) provides a set of algorithmic skeletons as a C++ library on top of MPI. The parallel programming approach of OSL is a structured one, which eases the reasoning about the performance and correctness of the programs. In this paper we present the verification of a heat diffusion simulation program, written in OSL, using...

Orleans Skeleton Library (OSL) is a library of parallel algorithmic skeletons in C++ on top of MPL It provides a structured approach towards parallel programming. Skeletons in OSL are based over the bulk synchronous parallelism model. Applications can be developed using different combinations and compositions of the skeletons. This paper illustrate...

Algorithmic skeletons are a high-level approach to parallel programming that can be combined with widely used programming languages such as Java, C and C++. In this paper we show that prototyping such a library with a structured parallel functional language, namely Bulk Syn-chronous Parallel ML, provides a parallel implementation with which experim...

The existing solutions to program parallel architectures range from parallelizing compilers to distributed concurrent programming. Intermediate approaches propose a more structured parallelism: Algorithmic skeletons are higher-order functions that capture the patterns of parallel algorithms. The user of the library has just to compose some of the s...

International Conference for High Performance Computing, Networking, Storage and Analysis (SC08), Poster