More Like this

1. Brain–machine interface based on deep learning to control asynchronously a lower-limb robotic exoskeleton: a case-of-study

   https://doi.org/10.1186/s12984-024-01342-9  

   Ferrero, Laura; Soriano-Segura, Paula; Navarro, Jacobo; Jones, Oscar; Ortiz, Mario; Iáñez, Eduardo; Azorín, José M; Contreras-Vidal, José L (April 2024, Journal of NeuroEngineering and Rehabilitation)

   Abstract BackgroundThis research focused on the development of a motor imagery (MI) based brain–machine interface (BMI) using deep learning algorithms to control a lower-limb robotic exoskeleton. The study aimed to overcome the limitations of traditional BMI approaches by leveraging the advantages of deep learning, such as automated feature extraction and transfer learning. The experimental protocol to evaluate the BMI was designed as asynchronous, allowing subjects to perform mental tasks at their own will. MethodsA total of five healthy able-bodied subjects were enrolled in this study to participate in a series of experimental sessions. The brain signals from two of these sessions were used to develop a generic deep learning model through transfer learning. Subsequently, this model was fine-tuned during the remaining sessions and subjected to evaluation. Three distinct deep learning approaches were compared: one that did not undergo fine-tuning, another that fine-tuned all layers of the model, and a third one that fine-tuned only the last three layers. The evaluation phase involved the exclusive closed-loop control of the exoskeleton device by the participants’ neural activity using the second deep learning approach for the decoding. ResultsThe three deep learning approaches were assessed in comparison to an approach based on spatial features that was trained for each subject and experimental session, demonstrating their superior performance. Interestingly, the deep learning approach without fine-tuning achieved comparable performance to the features-based approach, indicating that a generic model trained on data from different individuals and previous sessions can yield similar efficacy. Among the three deep learning approaches compared, fine-tuning all layer weights demonstrated the highest performance. ConclusionThis research represents an initial stride toward future calibration-free methods. Despite the efforts to diminish calibration time by leveraging data from other subjects, complete elimination proved unattainable. The study’s discoveries hold notable significance for advancing calibration-free approaches, offering the promise of minimizing the need for training trials. Furthermore, the experimental evaluation protocol employed in this study aimed to replicate real-life scenarios, granting participants a higher degree of autonomy in decision-making regarding actions such as walking or stopping gait. 

   more » « less
2. Simultaneous Bayesian Calibration and Engineering Design With an Application to a Vibration Isolation System

   https://doi.org/10.1115/1.4050075  

   Ehrett, Carl; Brown, D. Andrew; Kitchens, Christopher; Xu, Xinyue; Platz, Roland; Atamturktur, Sez (March 2021, Journal of Verification, Validation and Uncertainty Quantification)

   null (Ed.)

   Abstract Calibration of computer models and the use of those design models are two activities traditionally carried out separately. This paper generalizes existing Bayesian inverse analysis approaches for computer model calibration to present a methodology combining calibration and design in a unified Bayesian framework. This provides a computationally efficient means to undertake both tasks while quantifying all relevant sources of uncertainty. Specifically, compared with the traditional approach of design using parameter estimates from previously completed model calibration, this generalized framework inherently includes uncertainty from the calibration process in the design procedure. We demonstrate our approach to the design of a vibration isolation system. We also demonstrate how, when adaptive sampling of the phenomenon of interest is possible, the proposed framework may select new sampling locations using both available real observations and the computer model. This is especially useful when a misspecified model fails to reflect that the calibration parameter is functionally dependent upon the design inputs to be optimized. 

   more » « less
3. Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach

   Li, Dongyue; Zhang, Ziniu; Wang, Lu; Zhang, Hongyang R (November 2024, Findings of the Association for Computational Linguistics: EMNLP 2024)

   We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from n auxiliary tasks. This problem has broad applications in NLP, such as targeted instruction tuning and data selection in chain-of-thought fine-tuning. The key challenge of this problem is that not all auxiliary tasks are useful to improve the performance of the target task. Thus, choosing the right subset of auxiliary tasks is crucial. Conventional subset selection methods, such as forward & backward selection, are unsuitable for LM fine-tuning because they require repeated training on subsets of auxiliary tasks. This paper introduces a new algorithm to estimate model fine-tuning performances without repeated training. Our algorithm first performs multitask training using the data of all the tasks to obtain a meta initialization. Then, we approximate the model fine-tuning loss of a subset using functional values and gradients from the meta initialization. Empirically, we find that this gradient-based approximation holds with remarkable accuracy for twelve transformer-based LMs. Thus, we can now estimate fine-tuning performances on CPUs within a few seconds. We conduct extensive experiments to validate our approach, delivering a speedup of 30× over conventional subset selection while incurring only 1% error of the true fine-tuning performances. In downstream evaluations of instruction tuning and chain-of-thought fine-tuning, our approach improves over prior methods that utilize gradient or representation similarity for subset selection by up to 3.8%. 

   more » « less
4. A Kernel-Based View of Language Model Fine-Tuning

   Malladi, Sadhika; Wettig, Alexander; Yu, Dingli; Chen, Danqi; Arora, Sanjeev. (July 2023, Proceedings of the 40th International Conference on Machine Learning)

   It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings. There is minimal theoretical understanding of empirical success, e.g., why fine-tuning a model with $10^8$ or more parameters on a couple dozen training points does not result in overfitting. We investigate whether the Neural Tangent Kernel (NTK)—which originated as a model to study the gradient descent dynamics of infinitely wide networks with suitable random initialization—describes fine-tuning of pre-trained LMs. This study was inspired by the decent performance of NTK for computer vision tasks (Wei et al., 2022). We extend the NTK formalism to Adam and use Tensor Programs (Yang, 2020) to characterize conditions under which the NTK lens may describe fine-tuning updates to pre-trained language models. Extensive experiments on 14 NLP tasks validate our theory and show that formulating the downstream task as a masked word prediction problem through prompting often induces kernel-based dynamics during fine-tuning. Finally, we use this kernel view to propose an explanation for the success of parameter-efficient subspace-based fine-tuning methods. 

   more » « less
5. LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses

   Liu, Xin; Khalifa, Muhammad; Wang, Lu (May 2024, Proceedings of the International Conference on Learning Representations (ICLR))

   A model is considered well-calibrated when its probability estimate aligns with the actual likelihood of the output being correct. Calibrating language models (LMs) is crucial, as it plays a vital role in detecting and mitigating hallucinations of LMs as well as building more trustworthy models. However, standard calibration techniques may not be suited for LM calibration. For instance, post-processing methods such as temperature scaling do not reorder the candidate generations. On the other hand, training-based methods require fine-tuning the entire model, which is impractical for LMs of large scale. We present LITCAB, a lightweight calibration mechanism consisting of a single linear layer that takes the input text representation and predicts a bias term, which is then added to the LM output logits. LITCAB improves model calibration by only adding < 2% of the original model parameters. For evaluation, we construct CAT, a benchmark consisting of eight text generation tasks, covering responses ranging from short phrases to paragraphs. We test LITCAB with Llama2-7B, where it improves calibration across all tasks, reducing the average ECE score by as large as 30%. We further conduct a comprehensive evaluation with multiple popular open-sourced LMs from GPT and LLaMA families, yielding the following key findings: (i) Larger models within the same family exhibit better calibration on tasks with short generation tasks, but not necessarily for longer ones. (ii) GPT-family models show superior calibration compared to LLaMA, Llama2, and Vicuna models, despite having much fewer parameters. (iii) Fine-tuning pretrained model (e.g., LLaMA) with samples of limited purpose (e.g., conversations) may lead to worse calibration, highlighting the importance of fine-tuning setups for calibrating LMs. 

   more » « less