Evolution of laughter from play.

In this hypothesis, I discuss how laughter from physical play could have evolved to being induced via visual or even verbal stimuli, and serves as a signal to highlight incongruity that could potentially pose a threat to survival. I suggest how laughter's induction could have negated the need for physical contact in play, evolving from its use in tickling, to tickle-misses, and to taunting, and I discuss how the application of deep learning neural networks trained on images of spectra of a variety of laughter types from a variety of individuals or even species, could be used to determine such evolutionary pathways via the use of latent space exploration.

Single-step phase identification and phase locking for coherent beam combination using deep learning.

Coherent beam combination offers a solution to the challenges associated with the power handling capacity of individual fibres, however, the combined intensity profile strongly depends on the relative phase of each fibre. Optimal combination necessitates precise control over the phase of each fibre channel, however, determining the required phase compensations is challenging because phase information is typically not available. Additionally, the presence of continuously varying phase noise in fibre laser systems means that a single-step and high-speed correction process is required. In this work, we use a spatial light modulator to demonstrate coherent combination in a seven-beam system. Deep learning is used to identify the relative phase offsets for each beam directly from the combined intensity pattern, allowing real-time correction. Furthermore, we demonstrate that the deep learning agent can calculate the phase corrections needed to achieve user-specified target intensity profiles thus simultaneously achieving both beam combination and beam shaping.

Live imaging of laser machining via plasma deep learning.

Real-time imaging of laser materials processing can be challenging as the laser generated plasma can prevent direct observation of the sample. However, the spatial structure of the generated plasma is strongly dependent on the surface profile of the sample, and therefore can be interrogated to indirectly provide an image of the sample. In this study, we demonstrate that deep learning can be used to predict the appearance of the surface of silicon before and after the laser pulse, in real-time, when being machined by single femtosecond pulses, directly from camera images of the generated plasma. This demonstration has immediate impact for real-time feedback and monitoring of laser materials processing where direct observation of the sample is not possible.

Acoustic and plasma sensing of laser ablation via deep learning.

Monitoring laser ablation when using high power lasers can be challenging due to plasma obscuring the view of the machined sample. Whilst the appearance of the generated plasma is correlated with the laser ablation conditions, extracting useful information is extremely difficult due to the highly nonlinear processes involved. Here, we show that deep learning can enable the identification of laser pulse energy and a prediction for the appearance of the ablated sample, directly from camera images of the plasma generated during single-pulse femtosecond ablation of silica. We show that this information can also be identified directly from the acoustic signal recorded during this process. This approach has the potential to enhance real-time feedback and monitoring of laser materials processing in situations where the sample is obscured from direct viewing, and hence could be an invaluable diagnostic for laser-based manufacturing.

Motion control for laser machining via reinforcement learning.

Laser processing techniques such as laser machining, marking, cutting, welding, polishing and sintering have become important tools in modern manufacturing. A key step in these processes is to take the intended design and convert it into coordinates or toolpaths that are useable by the motion control hardware and result in efficient processing with a sufficiently high quality of finish. Toolpath design can require considerable amounts of skilled manual labor even when assisted by proprietary software. In addition, blind execution of predetermined toolpaths is unforgiving, in the sense that there is no compensation for machining errors that may compromise the quality of the final product. In this work, a novel laser machining approach is demonstrated, utilizing reinforcement learning (RL) to control and supervise the laser machining process. This autonomous RL-controlled system can laser machine arbitrary pre-defined patterns whilst simultaneously detecting and compensating for incorrectly executed actions, in real time.

Single-frame 3D lensless microscopic imaging via deep learning.

Since the pollen of different species varies in shape and size, visualizing the 3-dimensional structure of a pollen grain can aid in its characterization. Lensless sensing is useful for reducing both optics footprint and cost, while the capability to image pollen grains in 3-dimensions using such a technique could be truly disruptive in the palynology, bioaerosol sensing, and ecology sectors. Here, we show the ability to employ deep learning to generate 3-dimensional images of pollen grains using a series of 2-dimensional images created from 2-dimensional scattering patterns. Using a microscope to obtain 3D Z-stack images of a pollen grain and a 520 nm laser to obtain scattering patterns from the pollen, a single scattering pattern per 3D image was obtained for each position of the pollen grain within the laser beam. In order to create a neural network to transform a single scattering pattern into different 2D images from the Z-stack, additional Z-axis information is required to be added to the scattering pattern. Information was therefore encoded into the scattering pattern image channels, such that the scattering pattern occupied the red channel, and a value indicating the position in the Z-axis occupied the green and blue channels. Following neural network training, 3D images were formed from collated generated 2D images. The volumes of the pollen grains were generated with a mean accuracy of ∼84%. The development of airborne-pollen sensors based on this technique could enable the collection of rich data that would be invaluable to scientists for understanding mechanisms of pollen production climate change and effects on the wider public health.

Deep-Learning-Assisted Focused Ion Beam Nanofabrication.

Focused ion beam (FIB) milling is an important rapid prototyping tool for micro- and nanofabrication and device and materials characterization. It allows for the manufacturing of arbitrary structures in a wide variety of materials, but establishing the process parameters for a given task is a multidimensional optimization challenge, usually addressed through time-consuming, iterative trial-and-error. Here, we show that deep learning from prior experience of manufacturing can predict the postfabrication appearance of structures manufactured by focused ion beam (FIB) milling with >96% accuracy over a range of ion beam parameters, taking account of instrument- and target-specific artifacts. With predictions taking only a few milliseconds, the methodology may be deployed in near real time to expedite optimization and improve reproducibility in FIB processing.

Single step phase optimisation for coherent beam combination using deep learning.

Coherent beam combination of multiple fibres can be used to overcome limitations such as the power handling capability of single fibre configurations. In such a scheme, the focal intensity profile is critically dependent upon the relative phase of each fibre and so precise control over the phase of each fibre channel is essential. Determining the required phase compensations from the focal intensity profile alone (as measured via a camera) is extremely challenging with a large number of fibres as the phase information is obfuscated. Whilst iterative methods exist for phase retrieval, in practice, due to phase noise within a fibre laser amplification system, a single step process with computational time on the scale of milliseconds is needed. Here, we show how a neural network can be used to identify the phases of each fibre from the focal intensity profile, in a single step of ~ 10 ms, for a simulated 3-ring hexagonal close-packed arrangement, containing 19 separate fibres and subsequently how this enables bespoke beam shaping. In addition, we show that deep learning can be used to determine whether a desired intensity profile is physically possible within the simulation. This, coupled with the demonstrated resilience against simulated experimental noise, indicates a strong potential for the application of deep learning for coherent beam combination.

Identification of spatial intensity profiles from femtosecond laser machined depth profiles via neural networks.

Laser machining involves many complex processes, especially when using femtosecond pulses due to the high peak intensities involved. Whilst conventional modelling, such as those based on photon-electron interactions, can be used to predict the appearance of the surface after machining, this generally becomes unfeasible for micron-scale features and larger. The authors have previously demonstrated that neural networks can simulate the appearance of a sample when machined using different spatial intensity profiles. However, using a neural network to model the reverse of this process is challenging, as diffractive effects mean that any particular sample appearance could have been produced by a large number of beam shape variations. Neural networks struggle with such one-to-many mappings, and hence a different approach is needed. Here, we demonstrate that this challenge can be solved by using a neural network loss function that is a separate neural network. Here, we therefore present a neural network that can identify the spatial intensity profiles needed, for multiple laser pulses, to produce a specific depth profile in 5 µm thick electroless nickel.

Modelling of fibre laser cutting via deep learning.

Laser cutting is a materials processing technique used throughout academia and industry. However, defects such as striations can be formed while cutting, which can negatively affect the final quality of the cut. As the light-matter interactions that occur during laser machining are highly non-linear and difficult to model mathematically, there is interest in developing novel simulation methods for studying these interactions. Deep learning enables a data-driven approach to the modelling of complex systems. Here, we show that deep learning can be used to determine the scanning speed used for laser cutting, directly from microscope images of the cut surface. Furthermore, we demonstrate that a trained neural network can generate realistic predictions of the visual appearance of the laser cut surface, and hence can be used as a predictive visualisation tool.

The future of bone regeneration: integrating AI into tissue engineering.

Tissue engineering is a branch of regenerative medicine that harnesses biomaterial and stem cell research to utilise the body's natural healing responses to regenerate tissue and organs. There remain many unanswered questions in tissue engineering, with optimal biomaterial designs still to be developed and a lack of adequate stem cell knowledge limiting successful application. Advances in artificial intelligence (AI), and deep learning specifically, offer the potential to improve both scientific understanding and clinical outcomes in regenerative medicine. With enhanced perception of how to integrate artificial intelligence into current research and clinical practice, AI offers an invaluable tool to improve patient outcome.

Modeling adult skeletal stem cell response to laser-machined topographies through deep learning.

The response of adult human bone marrow stromal stem cells to surface topographies generated through femtosecond laser machining can be predicted by a deep neural network. The network is capable of predicting cell response to a statistically significant level, including positioning predictions with a probability P < 0.001, and therefore can be used as a model to determine the minimum line separation required for cell alignment, with implications for tissue structure development and tissue engineering. The application of a deep neural network, as a model, reduces the amount of experimental cell culture required to develop an enhanced understanding of cell behavior to topographical cues and, critically, provides rapid prediction of the effects of novel surface structures on tissue fabrication and cell signaling.

Modelling laser machining of nickel with spatially shaped three pulse sequences using deep learning.

Femtosecond laser machining is a complex process, owing to the high peak intensities involved. Modelling approaches for the prediction of final sample quality based on photon-atom interactions are therefore challenging to extrapolate up to the microscale and beyond. The problem is compounded when multiple exposures are used to produce a final structure, where surface modifications from previous exposures must be taken into consideration. Neural network approaches allow for the automatic creation of a model that accounts for these challenging processes, without any physical knowledge of the processes being programmed by a specialist. We present such a network for the prediction of surface quality for multi-exposure femtosecond machining on a 5µm electroless nickel layer deposited on copper, where each pulse is uniquely spatially shaped using a spatial light modulator. This neural network modelling method accurately predicts the surface profile after three, sequential, overlapping exposures of dissimilar intensity patterns. It successfully reproduces such effects as the sub-diffraction limit machining feasible with multiple exposures, and the smoothing effect on edge-burr from previous exposures expected in multi-exposure laser machining.

Real-time particle pollution sensing using machine learning.

Particle pollution is a global health challenge that is linked to around three million premature deaths per year. There is therefore great interest in the development of sensors capable of precisely quantifying both the number and type of particles. Here, we demonstrate an approach that leverages machine learning in order to identify particulates directly from their scattering patterns. We show the capability for producing a 2D sample map of spherical particles present on a coverslip, and also demonstrate real-time identification of a range of particles including those from diesel combustion.

Predictive capabilities for laser machining via a neural network.

The interaction between light and matter during laser machining is particularly challenging to model via analytical approaches. Here, we show the application of a statistical approach that constructs a model of the machining process directly from experimental images of the laser machined sample, and hence negating the need for understanding the underlying physical processes. Specifically, we use a neural network to transform a laser spatial intensity profile into an equivalent scanning electron microscope image of the laser-machined target. This approach enables the simulated visualization of the result of laser machining with any laser spatial intensity profile, and hence demonstrates predictive capabilities for laser machining. The trained neural network was found to have encoded functionality that was consistent with the laws of diffraction, hence showing the potential of this approach for discovering physical laws directly from experimental data.

Multiple Class I and Class II Haemophilus ducreyi Strains Cause Cutaneous Ulcers in Children on an Endemic Island.

Background: Together with Treponema pallidum subspecies pertenue, Haemophilus ducreyi is a major cause of exudative cutaneous ulcers (CUs) in children. For H. ducreyi, both class I and class II strains, asymptomatic colonization, and environmental reservoirs have been found in endemic regions, but the epidemiology of this infection is unknown. Methods: Based on published whole-genome sequences of H. ducreyi CU strains, a single-locus typing system was developed and applied to H. ducreyi-positive CU samples obtained prior to, 1 year after, and 2 years after the initiation of a mass drug administration campaign to eradicate CU on Lihir Island in Papua New Guinea. DNA from the CU samples was amplified with class I and class II dsrA-specific primers and sequenced; the samples were classified into dsrA types, which were geospatially mapped. Selection pressure analysis was performed on the dsrA sequences. Results: Thirty-seven samples contained class I sequences, 27 contained class II sequences, and 13 contained both. There were 5 class I and 4 class II types circulating on the island; 3 types accounted for approximately 87% of the strains. The composition and geospatial distribution of the types varied little over time and there was no evidence of selection pressure. Conclusions: Multiple strains of H. ducreyi cause CU on an endemic island and coinfections are common. In contrast to recent findings with T. pallidum pertenue, strain composition is not affected by antibiotic pressure, consistent with environmental reservoirs of H. ducreyi. Such reservoirs must be addressed to achieve eradication of H. ducreyi.

Ultrafast multi-layer subtractive patterning.

Subtractive femtosecond laser machining using multiple pulses with different spatial intensity profiles centred on the same position on a sample has been used to fabricate surface relief structuring. A digital micromirror device was used as an intensity spatial light modulator, with a fixed position relative to the sample, to ensure optimal alignment between successive masks. Up to 50 distinct layers, 335 nm lateral spatial resolution and 2.6 µm maximum depth structures were produced. The lateral dimensions of the structures are approximately 40 µm. Surface relief structuring is shown to match intended depth profiles in a nickel substrate, and highly repeatable stitching of identical features in close proximity is also demonstrated.

Single-pulse ablation of multi-depth structures via spatially filtered binary intensity masks.

Digital micromirror devices (DMDs) show great promise for use as intensity spatial light modulators. When used in conjunction with pulsed lasers of a timescale below the DMD pixel switching time, DMDs are generally only used as binary intensity masks (i.e., "on" or "off" intensity for each mask pixel). In this work, we show that by exploiting the numerical aperture of an optical system during the design of binary masks, near-continuous intensity control can be accessed, whilst still maintaining high-precision laser-machining resolution. Complex features with ablation depths up to ∼60 nm, corresponding to grayscale values in bitmap images, are produced in single pulses via ablation with 150 fs laser pulses on nickel substrates, with lateral resolutions of ∼2.5 µm.

Sub-diffraction limit laser ablation via multiple exposures using a digital micromirror device.

We present the use of digital micromirror devices as variable illumination masks for pitch-splitting multiple exposures to laser machine the surfaces of materials. Ultrafast laser pulses of length 150 fs and 800 nm central wavelength were used for the sequential machining of contiguous patterns on the surface of samples in order to build up complex structures with sub-diffraction limit features. Machined patterns of tens to hundreds of micrometers in lateral dimensions with feature separations as low as 270 nm were produced in electroless nickel on an optical setup diffraction limited to 727 nm, showing a reduction factor below the Abbe diffraction limit of ∼2.7×. This was compared to similar patterns in a photoresist optimized for two-photon absorption, which showed a reduction factor of only 2×, demonstrating that multiple exposures via ablation can produce a greater resolution enhancement than via two-photon polymerization.

A model system to mimic environmentally active surface film roughness and hydrophobicity.

This work presents the development and initial assessment of a laboratory platform to allow quantitative studies on model urban films. The platform consists of stearic acid and eicosane mixtures that are solution deposited from hexanes onto smooth, solid substrates. We show that this model has distinctive capabilities to better mimic a naturally occurring film's morphology and hydrophobicity, two important parameters that have not previously been incorporated into model film systems. The physical and chemical properties of the model films are assessed using a variety of analytical instruments. The film thickness and roughness are probed via atomic force microscopy while the film composition, wettability, and water uptake are analyzed by Fourier transform infrared spectroscopy, contact angle goniometry, and quartz crystal microbalance, respectively. Simulated environmental maturation is achieved by exposing the film to regulated amounts of UV/ozone. Ultimately, oxidation of the film is monitored by the analytical techniques mentioned above and proceeds as expected to produce a utile model film system. Including variable roughness and tunable surface coverage results in several key advantages over prior model systems, and will more accurately represent native urban film behavior.