Łukasz Laskowski

A novel hybrid-maximum neural network in stereo-matching process.

In the present paper, the completely innovative architecture of artificial neural network based on Hopfield structure for solving a stereo-matching problem—hybrid neural network, consisting of the classical analog Hopfield neural network and the Maximum Neural Network—is described. The application of this kind of structure as a part of assistive device for visually impaired individuals is considered. The role of the analog Hopfield network is to find the attraction area of the global minimum, whereas Maximum Neural Network is finding accurate location of this minimum. The network presented here is characterized by an extremely high rate of work performance with the same accuracy as a classical Hopfield-like network, which makes it possible to use this kind of structure as a part of systems working in real time. The network considered here underwent experimental tests with the use of real stereo pictures as well as simulated stereo images. This enables error calculation and direct comparison with the classic analog Hopfield neural network as well as other networks proposed in the literature.

Spin-glass Implementation of a Hopfield Neural Structure

Paper presents the hardware implementation of the Hopfield continuous neural network. We propose a molecular realization of a spin glass model. In particular, we consider a spin glass like structure that allows interconnection strengths change and neuron state test. Proposed device is based on SBA-15 mesoporous silica thin film, activated by Mn 12 molecular magnets. Our idea seems to be feasible from the technological point of view.

Objects auto-selection from stereo-images realised by self-correcting neural network

In the present thesis the author undertakes the problem of the objects selecting on pictures. The novel conception of using depth map as a base to objects marking was proposed here. objects separation can be done on the base of depth (disparity), corresponding to points that should be marked. This allows for elimination of textures, occurring in background and also on objects. The object selection process must be preceded by pictures depth analysis. This can be done by the novel neural structure: Self-Correcting Neural Network. This structure is working point-by-point with no pictures segmentation before.

Molecular Approach to Hopfield Neural Network

The present article puts forward a completely new technology development , a spin glass-like molecular implementation of the Hopfield neural structure. This novel approach uses magnetic molecules homogenously distributed in mesoporous silica matrix, which forms a base for a converting unit, an equivalent of a neuron in the Hopfield network. Converting units interact with each other via a fully controlled magnetic fields, which corresponds to weighted interconnections in the Hopfield network. This novel technology enables building fast, high-density content addressable associative memories. In particular, it is envisaged that in the future this approach can be scaled up to mimic memory with human-like characteristics. This would be a breakthrough in artificial brain implementations and usher in a new type of highly intelligent beings. Another application relates to systems designed for multi-objective optimization (multiple criteria decision making).

Iron Doped SBA-15 Mesoporous Silica Studied by Mössbauer Spectroscopy

Mesoporous silica SBA-15 containing propyl-iron-phosphonate groups were considered to confirm their molecular structure. To detect the iron-containing group configuration the Mossbauer spectroscopy was used. Both mesoporous silica SBA-15 containing propyl-iron-phosphonate groups and pure doping agent iron acetylacetate were investigated using Mossbauer spectroscopy. The parameters such as isomer shift, quadrupole splitting, and asymmetry in 57Fe Mossbauer spectra were analyzed. The differences in Mossbauer spectra were explained assuming different local surroundings of Fe nuclei. On this base we were able to conclude about activation of phosphonate units by iron ions and determinate the oxidation state of the metal ion. To examine bonding between iron atoms and phosphonic units the resonance Raman spectroscopy was applied. The density functional theory DFT approach was used to make adequate calculations. The distribution of active units inside silica matrix was estimated by comparison of calculated vibrational spectra with the experimental ones. Analysis of both Mossbauer and resonance Raman spectra seems to confirm the correctness of the synthesis procedure. Also EDX elemental analysis confirms our conclusions.

Relaxation and magnetocaloric effect in the Mn12 molecular nanomagnet incorporated into mesoporous silica: a comparative study

This paper presents the synthesis and investigation of the magnetic properties of mesoporous silica SBA-15 functionalized with Mn12 ([Mn12O12(CH3COO)16(H2O)4]·2CH3COOH·4H2O) high-spin molecular clusters. The SBA-Mn12 sample has been examined by means of X-ray diffraction, infrared spectroscopy, nitrogen sorption and TEM techniques. AC and DC magnetic measurements, including measurements of the magnetocaloric effect (MCE) were carried out both for SBA-Mn12 and for polycrystalline Mn12. An increase in the activation energy and in the distribution of relaxation times was observed for SBA-Mn12 as compared to those of Mn12. Differences in the MCE were also revealed. The maximum magnetic entropy change at the field change of 50 kOe for SBA-Mn12 is equal to 13.8 J K−1 mol−1 at T = 2.8 K, which is significantly less than 25.3 J K−1 mol−1 observed for Mn12 at 3.2 K. The altered relaxation and the magnetocaloric effect point to a successful incorporation of Mn12 molecules into the silica channels.

Influence of the Copper-Containing SBA-15 Silica Fillers on the Mechanical Properties of High Density Polyethylene

The paper concerns the mechanical properties of the high density polyethylene (HDPE) with the copper-containing SBA-15 silica filler. The considered filler is the SBA-15 mesoporous silica containing copper ions bounded inside channels via propyl-phosphonate anchoring groups. With its help, we can impart the biocidal properties to this plastic. Research covered mechanical properties, thermal analysis, colour, shine, and nanomolecular structure. Dynamical properties of the samples like modulus changes and mechanical core loss angle tangent versus temperature and vibration frequency were tested using DMTA method. Level of crystallinity was tested using DSC method while their structure was observed with going through light by optical microscope. Hardness and toughness of obtained samples were also defined. Colour and shine changes of the samples were observed for PE-HD with filler contents 0.5% and 1%. Modulus value changes versus temperature and frequency were notified for the samples with modifier. There were no differences in modulus changes versus temperature for samples with and without filler and frequencies 1 and 10 Hz. It was detected that melting enthalpy of the samples with the modifier decreases. Moreover, some influence of the samples with filler on colour and shine was observed.

Extensions of Hopfield Neural Networks for Solving of Stereo-Matching Problem

Paper considers three Hopfield based architectures in the stereo matching problem solving. Together with classical analogue Hopfield structure two novel architectures are examined: Hybrid-Maximum Neural Network and Self Correcting Neural Network.Energy functions that are crucial for the network performance and working algorithm are also presented.All considered structures are tested to compare their performance features. Two of them are particularly important: accuracy and computational time. For the experiment real and simulated stereo images are used. Obtained results lead to the conclusion about feasibility of considered architectures in the stereo matching problem solving for real time applications.

System for independent living --- new opportunity for visually impaired

The authors present the solution that supports the visually impaired persons. Proposed solution can help them to be more independent in everyday life. Described system will be able to assist the blind in unknown environment (stereo-vision based depth analysis module), to recognise familiar persons and read texts and labels. All information gathered by stereo-vision module and processed by the system (about obstacles in surrounding, result of face recognition, texts in visual field) will be available for the user thanks to tactile interface and the sound system. Considered here device can also help in moving around (system can be connected to a small vehicle).

The Concept of Molecular Neurons

The paper concerns the main element of the molecular neural network - the Molecular Neuron (MN). Molecular Neural Network idea has been introduced in our previous articles. Here we present the structure of the Molecular Neuron element in micro and nanoscale. We have obtained MN in hexagonal layout in the form of the thin film. In this paper we have described self-assembly mechanism leading to the NMs layout. Also physical properties of the MNs layer have been shown.