Active implantable medical devices (IMDs) require precise tissue stimulation to achieve effective therapeutic outcomes and ensure patient safety. This work introduces an 8-bit programmable current source, capable of delivering biphasic stimulation pulses from -25.5 mA to +25.5 mA in 0.1 mA steps, suitable for common IMD applications. The circuit supports pulses as short as a few microseconds, with measured settling times under 1 μs. The system includes a charge mismatch measurement circuit, and a 5-bit trimming mechanism to minimize the net charge delivered to the tissue. Fabricated in a 180 nm high-voltage CMOS technology, the circuit occupies less than 4 mm2, including a RISC-V processor, and I/O pads. Measurement results from the fabricated circuit are provided to validate the design.

This paper presents a system-on-chip (SoC) architecture for an active implantable microsystem that combines electrical recording with optogenetic stimulation for closed-loop neuromodulation. The SoC is designed to support a 4-shank optrode (opto-electrode) fork with 8 differential recording channels (0.1-5000Hz bandwidth, 10mVpp range, 12-bit resolution) to observe neural signals on electrodes and 32 driver circuits (2mA range, 6-bit current resolution with μs timing resolution) for microLED optical stimulation. Each SoC additionally integrates diagnostic instrumentation to measure electrical resistance across any of its I/O lines. The SoC features a custom 4-wire interface that provides power and data communication across multiple chips using a shared bus allowing for multiple forks to be stacked to form two dimensional optrode arrays. Each chip has an independent controller that receives, interprets and executes commands, and can transmit neural data while simultaneously controlling LED outputs. The circuit is implemented in a 180nm CMOS process, with each chip occupying a 5mm×2.45mm silicon footprint, designed specifically to mount on the base of the silicon optrode fork.

As the demand for high channel counts and high-resolution recordings of neural activity continues to grow, the increased power and data rate generated impose hard constraints on the telemetry capabilities of wireless implantable neural interfaces. To address this challenge, this work presents a novel system architecture for a reconfigurable readout circuit. It provides per-channel data rate reduction and adaptable bandwidth to match the characteristics and evolution of the neural signals under non-ideal electrode-tissue interactions. The system consists of a 14-bit hybrid continuous-time/discrete-time delta-sigma (CT/DT-∆Σ) analog front-end (AFE) followed by event-based decimation (EBD) which exploits the inherent sparsity in neural signals. The proposed AFE and EBD co-design was simulated using artifact-laden nonhuman primate microwire recordings. Results demonstrate a dynamic range of 76 dB, ensuring artifact robustness, along with up to a two-order-of-magnitude reduction in output data rate and power-area decimation footprint per channel, offering flexibility for high-quality (14 dB NRMSE) and medium-quality (8 dB NRMSE) reconstructions, based on the characteristics of the neural signals recorded at each channel.

Much of the work in the field of group fairness addresses disparities between predefined groups based on protected features such as gender, age, and race, which need to be available at train, and often also at test, time. These approaches are static and retrospective, since algorithms designed to protect groups identified a priori cannot anticipate and protect the needs of different at-risk groups in the future. In this work we analyze the space of solutions for worst-case fairness beyond demographics, and propose Blind Pareto Fairness (BPF), a method that leverages no-regret dynamics to recover a fair minimax classifier that reduces worst-case risk of any potential subgroup of sufficient size, and guarantees that the remaining population receives the best possible level of service. BPF addresses fairness beyond demographics, that is, it does not rely on predefined notions of at-risk groups, neither at train nor at test time. Our experimental results show that the proposed framework improves worst-case risk in multiple standard datasets, while simultaneously providing better levels of service for the remaining population. The code is available at github.com/natalialmg/BlindParetoFairness

In this work we formulate and formally characterize group fairness as a multi-objective optimization problem, where each sensitive group risk is a separate objective. We propose a fairness criterion where a classifier achieves minimax risk and is Pareto-efficient w.r.t. all groups, avoiding unnecessary harm, and can lead to the best zero-gap model if policy dictates so. We provide a simple optimization algorithm compatible with deep neural networks to satisfy these constraints. Since our method does not require test-time access to sensitive attributes, it can be applied to reduce worst-case classification errors between outcomes in unbalanced classification problems. We test the proposed methodology on real case-studies of predicting income, ICU patient mortality, skin lesions classification, and assessing credit risk, demonstrating how our framework compares favorably to other approaches.

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels. Understanding the generalization properties of RL is one of the challenges of modern machine learning. Towards this goal, we analyze policy learning in the context of Partially Observable Markov Decision Processes (POMDPs) and formalize the dynamics of training levels as instances. We prove that, independently of the exploration strategy, reusing instances introduces significant changes on the effective Markov dynamics the agent observes during training. Maximizing expected rewards impacts the learned belief state of the agent by inducing undesired instance-specific speed-running policies instead of generalizable ones, which are sub-optimal on the training set. We provide generalization bounds to the value gap in train and test environments based on the number of training instances, and use insights based on these to improve performance on unseen levels. We propose training a shared belief representation over an ensemble of specialized policies, from which we compute a consensus policy that is used for data collection, disallowing instance-specific exploitation. We experimentally validate our theory, observations, and the proposed computational solution over the CoinRun benchmark.

Extracting the instantaneous heart rate (iHR) from face videos has been well studied in recent years. It is well known that changes in skin color due to blood flow can be captured using conventional cameras. One of the main limitations of methods that rely on this principle is the need of an illumination source. Moreover, they have to be able to operate under different light conditions. One way to avoid these constraints is using infrared cameras, allowing the monitoring of iHR under low light conditions. In this work, we present a simple, principled signal extraction method that recovers the iHR from infrared face videos. We tested the procedure on 7 participants, for whom we recorded an electrocardiogram simultaneously with their infrared face video. We checked that the recovered signal matched the ground truth iHR, showing that infrared is a promising alternative to conventional video imaging for heart rate monitoring, especially in low light conditions. Code is available at https://github.com/natalialmg/IR_iHR.

Data collection and sharing are pervasive aspects of modern society. This process can either be voluntary, as in the case of a person taking a facial image to unlock his/her phone, or incidental, such as traffic cameras collecting videos on pedestrians. An undesirable side effect of these processes is that shared data can carry information about attributes that users might consider as sensitive, even when such information is of limited use for the task. It is therefore desirable for both data collectors and users to design procedures that minimize sensitive information leakage. Balancing the competing objectives of providing meaningful individualized service levels and inference while obfuscating sensitive information is still an open problem. In this work, we take an information theoretic approach that is implemented as an unconstrained adversarial game between Deep Neural Networks in a principled, data-driven manner. This approach enables us to learn domain-preserving stochastic transformations that maintain performance on existing algorithms while minimizing sensitive information leakage.