With the prosperity of the Internet of Things (IoT) and artificial intelligence (AI), more and more edge devices have been deployed to enable intelligent applications. However, due to the limited energy budget and computation resources, it is challenging to deploy deep neural networks on edge devices directly. The energy consumption of the memory transfer between the processor and memory is a significant part of the total energy consumption, which is the bottleneck of traditional von Neumann architecture. Computation in memory (CIM) is a promising architecture that can significantly reduce this energy consumption by minimizing the data movement between the processor and memory. By utilizing the novel non-volatile memory (NVM) technology, the computation can be performed in the memory in analog domain, which can reduce the energy consumption and latency of the computation. However, the existing periphery of CIM architecture, which is responsible for converting the result of the computation in memory to the digital domain, is not energy-efficient and has a large area overhead. In this thesis, we propose a novel AI-based periphery for CIM architecture to address these issues. The proposed periphery is based on the neural network, which can be trained to convert the crossbar output to the digital domain with high accuracy. Multiple inputs, up to four crossbar columns with different significant levels, can be processed simultaneously and output the shift-and-add result in the digital domain in one shot, without the need for multiplexers or post-processing circuits. Moreover, a new coding scheme called natural Palindromic Coding (NPC), is proposed to encode the output of the neural network, which aims to mitigate the spectral bias of the neural network, where high-frequency components, like the least significant bit (LSB), are underrepresented. Benchmarking results show that the proposed AI-based periphery, with 4 parallel 4-bit inputs and 8-bit output, can achieve 81.16% accuracy or 99.5% accuracy with 1 unit step tolerance. Under the MNIST dataset, the proposed NPC can achieve an accuracy of 96.80%, compared with 97.07% of software inference. In addition, the proposed periphery can achieve 31.77× energy saving and 9× area saving compared with the state-of-the-art neural-network-based periphery, or up to 1.65× energy saving and 2.70× area saving compared with the state-of-the-art SAR-ADC-based periphery.

Neuromorphic systems offer a promising solution to the computational challenges of intra-cortical Brain-Computer Interfaces (iBCIs), leveraging the event-driven nature of biological neural networks for enhanced power efficiency and data scalability. The exponential growth in neural data rates due to advancements in high-density neural recording creates significant hurdles in data transmission and processing. This paper introduces a novel neuromorphic compression architecture that combines delta-modulated level crossing events with Spiking Neural Networks (SNNs) trained through a two-stage process with grouped inputs. The proposed system achieves a compression ratio exceeding 94× and a peak Signal-to-Noise and Distortion Ratio (SNDR ) of 22 dB compared to the signal without Local Field Potentials. This substantial improvement over existing methods drastically reduces data throughput making it ideal for implantable devices where resource constraints are critical. Validated on hippocampal and cerebellar datasets, our approach significantly outperforms state-of-the-art techniques in terms of computational and compression efficiency, SNDR, and memory usage—requiring just 384 bits per channel to store necessary data for processing and 18.07K Multiply and Accumulate operations (MACs) per spike. These findings underscore the potential of neuromorphic SNNs as a transformative technology for future iBCIs, advancing neural prosthetics and brain-machine interfaces.

Graph-based machine learning has seen significant growth during the past years with great advancements and applicability. These approaches mostly focus on pairwise interactions, neglecting the patterns of higher-order interactions which are common to complex systems. In real-world applications, we often encounter these types of signals that naturally associate with nodes, edges or sets of nodes (e.g. triangles). While the node signals have been well-studied by graph-based methods, the other signals have been researched in the recently emerging field of topological signal processing and machine learning. In this thesis, we are particularly interested in edge flow, which models the signals over the edges of a network by signal processing and learning tasks, centring on simplicial complexes. Examples of such networks can be traffic flows in a road network or water flows in a hydrological network. Recent literature in topological signal processing shows simplicial complex as a powerful and principled higher-order network model for edge flows.

In this thesis, we introduce PyTSPL, a Python library that provides reliable and user-friendly building blocks for interacting with simplicial complexes. The library aims to provide a unified platform to read network data in different formats, preprocess them and store them in a data structure such that their properties can be easily retrieved. Users can visualize the simplicial complex simply and effectively, enhancing the interpretability of complex structures and data flows. Additionally, the library provides functionality to analyze the simplicial complexes using various advanced signal processing techniques. The motivation behind developing this master’s thesis is to provide practical bridges to analysing and processing network data based on recent research methods with a unified Python library. While various tools exist for specific aspects of network analysis, there is a lack of unified platforms that integrate reading, processing, visualization, and advanced analysis of network data through topological frameworks, specifically for simplicial complexes. This library is a comprehensive solution encapsulating the entire workflow in a single environment.

Data-driven approaches are a promising new addition to the list of available strategies for solving Partial Differential Equations (PDEs). One such approach, the Principal Component Analysis-based Neural Network PDE solver, can be used to learn a mapping between two function spaces, corresponding to a PDE. However, the practical limitations of this approach are unclear. This paper seeks to investigate for which types of inputs and outputs this type of solver gives useful results. Using a dataset with inputs sampled from Gaussian Random Fields with different parameters, and outputs for Poisson's equation and the Heat equation, obtained by using a Finite Element solver, neural networks are trained, and their performance is evaluated. The method performs adequately for the chosen inputs, and patterns are found in the resulting error, which differ for each set of input parameters. Thus, for these equations, it seems that this method performs differently for different input distributions, but further research is necessary to investigate if these patterns will hold for other equations.

Solving Partial Differential Equations (PDEs) in engineering such as Navier-Stokes is incredibly computationally expensive and complex. Without analytical solutions, numerical solutions can take ages to simulate at great expense. In order to reduce this cost, neural networks may be used to compute approximations of the solution for use during engineering processes. PCA-net is a neural network approach that reduces the dimensionality of the input and output data for PDEs in order to allow mapping from a high-dimensional input and output function with a fully connected neural network through the use of Principal Component Analysis (PCA). In this paper, PCA-net is applied to Navier-Stokes with varying viscosities to test the generalization of PCA-net on viscosity parameters. Training is done on four discrete viscosities, while testing is done on continuous viscosities, extrapolating and interpolating around the training set. Results shows good performance on low viscosities, both with interpolation and extrapolation. Mid-to-high viscosity interpolation shows lesser performance, with high viscosity extrapolation diverging to great error. Omitting high viscosities, performance over varying viscosities is close to that shown by previous research.

This paper presents a comprehensive exploration of a novel method combining Principal Component Analysis (PCA) and Neural Networks (NN) to efficiently solve Partial Differential Equations (PDEs), a fundamental challenge in modeling a wide range of real-world phenomena. Our research extends the work of Bhattacharya et al. by focusing on PCA for effective dimensionality reduction and utilizing NN for mapping in the reduced dimension. This approach addresses the significant computational challenges and inaccuracies often encountered with classical numerical techniques in solving PDEs.

We specifically investigate the still-water equation, employing our PCA-NN method to learn a reduced order mapping of PDE solutions and evaluate its robustness in diverse noisy environments. Our findings reveal a notable relationship between noise intensity and error, indicating a linear trend for Gaussian and Salt and Pepper noise, and an exponential trend for Uniform noise. Furthermore, this study uncovers a critical weakness of the model in predicting points with a high rate of change.

Overall, our research significantly contributes to understanding the practical applicability and limitations of PCA-NN methods in real-world, noisy settings, offering valuable insights for future applications in this domain.

Batteryless Internet of Things (IoT) devices powered by energy harvesting enable sustainable and maintenance-free operation, but face challenges in achieving synchronised bidirectional communication between intermittently-powered nodes. This thesis presents CardioSync, a novel framework that leverages the human heartbeat as a shared clock to synchronise Bluetooth Low Energy (BLE) connections between battery less devices. CardioSync integrates a low-power optical heart rate sensor to capture real-time heartbeat data. A peak detection algorithm identifies distinct heart rate peaks, establishing synchronisation points for connection-setup events. By scheduling BLE advertising and scanning activities timed with detected peaks, CardioSync aligns connection attempts between intermittently-powered devices. This heartbeat-based synchronisation is integrated into the existing FreeBie architecture for intermittent BLE communication. Experimental evaluations demonstrate CardioSync's ability to successfully establish synchronised connections between batteryless nodes, reducing average connection setup time by up to 1.8x compared to an asynchronous FreeBie system. However, these gains incurred increased power consumption due to the integrated sensor. CardioSync enhances FreeBie's capabilities, enabling efficient intermittent-to-intermittent BLE connections. The proposed technique shows promise for advancing body sensor networks through sustainable and maintenance-free operation. Further work should optimise sensor utilisation and explore adaptive synchronisation to improve energy efficiency.

This study aims to investigate the impact of various denoising algorithms on the quality of visual stimulus reconstructions based on functional magnetic resonance imaging (fMRI) data. While fMRI provides a valuable, noninvasive method for assessing brain activity, the reliability of this data can be impaired by multiple noise types, including thermal, physiological, and scanner-related noise. Numerous denoising methods have been proposed, such as independent component analysis, confound regression and filtering, and GLM denoise. However, their efficiency, especially in the context of limited task fMRI data, remains largely unexplored. Using the Generic Objects Dataset (GOD), our study explores three primary research subquestions: the effectiveness of different denoising algorithms in improving reconstruction quality; the impact of artificially induced noise on these algorithms and whether combining different denoising algorithms can further enhance image reconstruction quality. The primary contributions of this research include the evaluation of various denoising methods with limited task fMRI data, determining the most effective denoising algorithms given a small dataset size, and analyzing how these algorithms perform in the presence of artificially introduced noise. The results of this investigation showed an improvement in performance of reconstruction models given multiple denoising algorithm, the best performer being kurtosis-based PCA used together with nuisanse regression with constant and linear terms bringing a 6.2% increase in score. The noise ceiling is the worst performer, bringing the score down by 4.4%. Denoising algorithms fail to improve reconstructions poisoned with gaussian noise, however, ICA manages to achieve a minor improvement of the quality of reconstructed images given noise sampled from the uniform distribution.

Image reconstruction from neural activation data is a field that has been growing in popularity with developments such as neuralink in the brain-machine interface space. To make better decisions when collecting data for this purpose, it is important to know what qualities to optimize for. The present paper investigates the relation between participant variation and visual stimulus reconstruction performance from functional magnetic resonance imaging (fMRI) data, which can guide decisions on whether resources should be spent collecting more data from fewer individuals or vice versa. We conducted performance evaluation on the Self-Supervised Image Reconstruction machine learning architecture proposed by Gaziv et al. using three pixel-wise and two structural image similarity measures. Our results show that reconstructions from one subject's fMRI data consistently performed best across all five performance metrics. However, statistically significant variance in reconstruction performance across subjects was found for only the feature-based similarity index. While the present paper found statistically significant results, we recommend future research to further investigate this notion by employing similar evaluation on other models.

Reconstructing seen images from functional magnetic resonance imaging (fMRI) brain scans has been a growing topic of interest in the field of neuroscience, fostered by innovation in machine learning and AI. This paper investigates the possible presence of personal features allowing the identification of subjects from their reconstructed images. Identifying the extent to which personal information is present is necessary to prevent privacy and data protection breaches. Additionally, personal features may reveal information about how people see the world, furthering work in computer-brain interfacing or helping people with neurological conditions that affect sight. In this paper, a CNN model is presented that allows to identify subjects from their reconstructed image with an average accuracy of 90.4%. An encoder-decoder model was used to produce the reconstructed images from the Generic Object Data set. The accuracy shows that personal features are indeed present in the reconstructed images, raising important ethical and legal considerations when using image reconstruction technology.

This study investigates the relationship between deep learning models and the human brain, specifically focusing on the prediction of brain activity in response to static visual stimuli using functional magnetic resonance imaging (fMRI). By leveraging intermediate outputs of pre-trained convolutional neural networks (CNNs) with feature-weighted receptive fields, it becomes possible to estimate brain activity in the visual cortex. The primary objective of this research is to analyze how different CNN architectures affect the accuracy of predicting brain activity. To accomplish this, we utilize the novel fMRI Natural Scenes Dataset, which provides a large-scale data set for comprehensive analysis. Through this investigation, we aim to gain insights into the impact of CNN architectures on the prediction accuracy of brain activity in the context of visual stimuli.

In modern neurosurgical practice, a surgeon can see a patient’s fiber tracts (nerve tracts) on a monitor in the operating room. This design study investigates the benefit of adding the uncertainty of the tracts and aims to improve the surgeon’s orientation while reducing visual clutter.

Based on an interview with a neurosurgeon and our experience during a surgery visit, we designed, implemented, and evaluated a new visualization method for intraoperative use. We present two new visualization techniques: a partial hull that appears when a surgeon approaches it and a distance meter that serves as a warning tool.

We conclude that there is a need for the intraoperative visualization of fiber uncertainty and recommend doing clinical trials using these methods.

Deep learning has been widely implemented in industrial inspection, such as damage detection from images. However, training deep networks requires massive data, which is hard to collect and laborious to annotate, especially in the aviation scenario of aircraft engines. To alleviate the demand for annotated data, we create BladeSynth - a large synthetic image dataset for detecting damage from aircraft engines, and empirically evaluate the transferability of state-of-the-art Scaled-YOLOV4 from synthetic to real world by pre-training on synthetic data and fine-tuning on real data. Our experiments show that pre-training on synthetic data improves the performance in damage detection in aircraft engine images.

In recent years, the expansion of the Internet has brought an explosion of visual information, including social media, medical photographs, and digital history. This massive amount of visual content generation and sharing presents new challenges, especially when searching for similar information in databases —— Content-Based Image Retrieval (CBIR). Feature extraction is the foundation of image retrieval, making research into obtaining concrete features and representations of image content a vital concern.
In the feature extraction module, We first pre-process the target image and input it into a CNN to obtain feature maps for different channels. These feature maps can be aggregated into compact and global uniform descriptors by pooling. Then these global descriptors are further dimensionalised and normalized by whitening methods to obtain image feature vectors that are easy to compute and compare. In this process, the accuracy of the retrieval depends on how accurately the final feature vectors represent the meaning expressed by the target image. Therefore, various CNN network structures, pooling and whitening methods are proposed to get more concrete feature vectors.
In this thesis, our study (1) fine tunes the pre-trained CNNs, (2) optimizes the application of second-order attention information in feature map, (3) applies and compares popular feature enhancement methods in both aggregating and whitening, (4) explores how to combine all strengths, and (5) propose a new model \textit{ResNet-SOI}, which achieves 53.4(M) and 59.2(M) mAP on the challenging benchmark \textit{ROxford5k+1M} and\textit{ RParis6k+1M}, and outperforms the state-of-art methods. Our prototype GUI is available on GitHub (https://github.com/yanan-huu/Image-Search-Engine-for-Historical-Research).

AI systems have the ability to complete tasks with greater precision and speed than humans, which has led to an increase in their usage. These systems are often grouped with humans in order to take advantage of the unique abilities of both the AI and the human. However, to make this cooperation as efficient as possible, there needs to be a mutual trust between humans and AIs. While there has been much research concerning the topic of human trust, there is a lack of work done concerning the trust that an artificial agent has toward its human partner. Given that a human must appear trustworthy to an artificial agent in order for that agent to trust him, and that demanding and offering help are important parts of a collaboration, the following research question has been formulated : How does an artificial agent asking a human for advice or help affect that human's trustworthiness ? To answer this research question, an experiment was conducted through an urban search and rescue game using the MATRX Software. Through this game, participants had to collaborate with a robot partner in order to accomplish the task of finding and rescuing 8 victims and delivering them to the correct drop zone. The participants were divided into a control group, who worked alongside a basic rescue robot, and an experimental group, which had a help-seeker robot as a partner. The help-seeker robot differed from the basic robot in its ability to ask the participant for advice, such as asking which room it should search for victims to rescue. Following the experiment, no significant results indicating a positive or negative effect on human trustworthiness by the help-seeker agent's behaviour were found.

Collaborative AI (CAI) is a fast growing field of study. Cooperation between teams composed of humans and artificial intelligence needs to be principled and founded on reciprocal trust. Modelling the trustworthiness of humans is a difficult task because of the ambiguous nature of its definition as well as the effect of team work dynamic. This research defines and measures human trustworthiness within the context of human-AI collaboration and tests how the artificial intelligence agent’s action of offering help plays a role in it. The experiment is conducted through the MATRX framework, in which a human agent and an AI agent collaborate in order to search and rescue victims within the environment. The ABI trust model is used to determine the sub-components that define trustworthiness, which is ability, benevolence and integrity. Trustworthiness is measured in 2 ways, through objective measures which represent the AI agent’s measure of the human trustworthiness and subjective measures that represent the human’s measure of their own trustworthiness. The results show that help offered by the AI agent, improves the ability and benevolence of the human agent in objective metrics but not integrity. Subjective results show no statistically significant change. The research concludes that the trustworthiness perceived by the AI agent is indeed improved, but does not provide evidence of the same from the perception of the human agent.

As technology advances, automated systems become more autonomous which leads to a higher interdependence between machine and human. Much research has been done about trust between humans and trust of humans regarding machines. An interesting question that remains is how the behavior of an agent influences human trustworthiness in a human-agent collaborative setting. The research presented by this paper contributes to the understanding of this area. It investigates a specific behavioral trait using the following hypothesis: friendly behavior of an agent improves human trustworthiness. Here, trustworthiness is broken up in the constructs: ability, benevolence and integrity.

An experiment has been conducted using a collaborative Search and Rescue game. The following behaviors of the participants have been measured:
- Ability: speed and effectiveness;
- Benevolence: communication, willingness to help, agreeableness to advice, responsiveness;
- Integrity: truthfulness.
Furthermore, a likert scale has been used to measure the participants' own perception of their trustworthiness. The experiment is conducted with 20 participants in the control group, where the agent spoke in a neutral manner, and 20 in the experimental group, where the agent instilled empathy, stimulated collaboration, encouraged the participants and was affectionate.

The research has shown a significant improvement in the experimental group only for communication and willingness to help. This gives some indication that a friendly agent only slightly improves the trustworthiness of a human. However, the research has some limitations that might also explain the lack of significant results. Firstly, it is unclear to what extent the measures truly measured the constructs of trustworthiness. Secondly, to create a friendly agent, theories from organizational and social psychology are used, which are mostly focussed on human-human relationships, instead of human-agent relationships. Finally, Some confounding variables may have had an impact, like lag in the game and the participant not properly reading the agent’s messages.

The number of collaborations between humans and artificial agents has risen steeply in recent years due to the rapid expansion of AI. Numerous studies in social sciences have already established that trust is a crucial factor in ensuring effective teamwork. While the dynamics of trust in human-human relationships or the effects of human comportment on the artificial agents' trustworthiness have been researched, the changes in human trustworthiness as a result of different AI behaviors were scarcely analysed. Therefore, the latter perspective needs to be thoroughly studied as well. This paper has investigated how an AI directing the human can affect human trustworthiness. So far, the directability has been studied as a notion on its own without being linked to trust or its effects on human-AI relationships. For this research, subjective and objective measurements have been used to assess the effects of an AI directing the human in joint activity. In order to quantify the human trustworthiness and assess the possible changes, an experiment has been carried out where participants played a Search & Rescue game developed in the MATRX software. The human's trustworthiness has been calculated using the ABI model and a questionnaire. The obtained results suggest that there is not a significant change in human trustworthiness as a result of the artificial agent directing the human.

Human-AI teams require trust to operate efficiently and solve certain tasks like search & rescue. Trustworthiness is measured using the ABI model; Ability, Benevolence and Integrity. This research paper tries to observe the effect a conflicting robot has on the human trustworthiness. The hypothesis we try to test is: “human trustworthiness will decrease when paired with a conflicting AI”. We conduct an experiment with one control group playing with a normal agent and an experiment group paired with the conflicting agent. Using the ABI concepts, we model the human trustworthiness across both groups using in-game observations (objective) and a questionnaire (subjective). When comparing the results from both group we see that the conflicting agent does not decrease the objective trustworthiness, however looking at the questionnaires we observe that the subjective human benevolence and integrity are negatively affected when paired with the conflicting agent.