Sarah J. Zhang, Samuel Florin, Ariel N. Lee et al.
We curate a comprehensive dataset of 4,550 questions and solutions from problem sets, midterm exams, and final exams across all MIT Mathematics and Electrical Engineering and Computer Science (EECS) courses required for obtaining a degree. We evaluate the ability of large language models to fulfill the graduation requirements for any MIT major in Mathematics and EECS. Our results demonstrate that GPT-3.5 successfully solves a third of the entire MIT curriculum, while GPT-4, with prompt engineering, achieves a perfect solve rate on a test set excluding questions based on images. We fine-tune an open-source large language model on this dataset. We employ GPT-4 to automatically grade model responses, providing a detailed performance breakdown by course, question, and answer type. By embedding questions in a low-dimensional space, we explore the relationships between questions, topics, and classes and discover which questions and classes are required for solving other questions and classes through few-shot learning. Our analysis offers valuable insights into course prerequisites and curriculum design, highlighting language models' potential for learning and improving Mathematics and EECS education.
Alexander E. Siemenn, Zekun Ren, Qianxiao Li et al.
Needle-in-a-Haystack problems exist across a wide range of applications including rare disease prediction, ecological resource management, fraud detection, and material property optimization. A Needle-in-a-Haystack problem arises when there is an extreme imbalance of optimum conditions relative to the size of the dataset. For example, only $0.82\%$ out of $146$k total materials in the open-access Materials Project database have a negative Poisson's ratio. However, current state-of-the-art optimization algorithms are not designed with the capabilities to find solutions to these challenging multidimensional Needle-in-a-Haystack problems, resulting in slow convergence to a global optimum or pigeonholing into a local minimum. In this paper, we present a Zooming Memory-Based Initialization algorithm, entitled ZoMBI. ZoMBI actively extracts knowledge from the previously best-performing evaluated experiments to iteratively zoom in the sampling search bounds towards the global optimum "needle" and then prunes the memory of low-performing historical experiments to accelerate compute times by reducing the algorithm time complexity from $O(n^3)$ to $O(φ^3)$ for $φ$ forward experiments per activation, which trends to a constant $O(1)$ over several activations. Additionally, ZoMBI implements two custom adaptive acquisition functions to further guide the sampling of new experiments toward the global optimum. We validate the algorithm's optimization performance on three real-world datasets exhibiting Needle-in-a-Haystack and further stress-test the algorithm's performance on an additional 174 analytical datasets. The ZoMBI algorithm demonstrates compute time speed-ups of 400x compared to traditional Bayesian optimization as well as efficiently discovering optima in under 100 experiments that are up to 3x more highly optimized than those discovered by similar methods MiP-EGO, TuRBO, and HEBO.
Alexander E. Siemenn, Eunice Aissi, Fang Sheng et al.
High-throughput materials synthesis methods have risen in popularity due to their potential to accelerate the design and discovery of novel functional materials, such as solution-processed semiconductors. After synthesis, key material properties must be measured and characterized to validate discovery and provide feedback to optimization cycles. However, with the boom in development of high-throughput synthesis tools that champion production rates up to $10^4$ samples per hour with flexible form factors, most sample characterization methods are either slow (conventional rates of $10^1$ samples per hour, approximately 1000x slower) or rigid (e.g., designed for standard-size microplates), resulting in a bottleneck that impedes the materials-design process. To overcome this challenge, we propose a set of automated material property characterization (autocharacterization) tools that leverage the adaptive, parallelizable, and scalable nature of computer vision to accelerate the throughput of characterization by 85x compared to the non-automated workflow. We demonstrate a generalizable composition mapping tool for high-throughput synthesized binary material systems as well as two scalable autocharacterization algorithms that (1) autonomously compute the band gap of 200 unique compositions in 6 minutes and (2) autonomously compute the degree of degradation in 200 unique compositions in 20 minutes, generating ultra-high compositional resolution trends of band gap and stability. We demonstrate that the developed band gap and degradation detection autocharacterization methods achieve 98.5% accuracy and 96.9% accuracy, respectively, on the FA$_{1-x}$MA$_{x}$PbI$_3$, $0\leq x \leq 1$ perovskite semiconductor system.
Vitali Petsiuk, Alexander E. Siemenn, Saisamrit Surbehera et al.
We provide a new multi-task benchmark for evaluating text-to-image models. We perform a human evaluation comparing the most common open-source (Stable Diffusion) and commercial (DALL-E 2) models. Twenty computer science AI graduate students evaluated the two models, on three tasks, at three difficulty levels, across ten prompts each, providing 3,600 ratings. Text-to-image generation has seen rapid progress to the point that many recent models have demonstrated their ability to create realistic high-resolution images for various prompts. However, current text-to-image methods and the broader body of research in vision-language understanding still struggle with intricate text prompts that contain many objects with multiple attributes and relationships. We introduce a new text-to-image benchmark that contains a suite of thirty-two tasks over multiple applications that capture a model's ability to handle different features of a text prompt. For example, asking a model to generate a varying number of the same object to measure its ability to count or providing a text prompt with several objects that each have a different attribute to identify its ability to match objects and attributes correctly. Rather than subjectively evaluating text-to-image results on a set of prompts, our new multi-task benchmark consists of challenge tasks at three difficulty levels (easy, medium, and hard) and human ratings for each generated image.
Siyu Isaac Parker Tian, Zekun Ren, Selvaraj Venkataraj et al.
Transfer learning increasingly becomes an important tool in handling data scarcity often encountered in machine learning. In the application of high-throughput thickness as a downstream process of the high-throughput optimization of optoelectronic thin films with autonomous workflows, data scarcity occurs especially for new materials. To achieve high-throughput thickness characterization, we propose a machine learning model called thicknessML that predicts thickness from UV-Vis spectrophotometry input and an overarching transfer learning workflow. We demonstrate the transfer learning workflow from generic source domain of generic band-gapped materials to specific target domain of perovskite materials, where the target domain data only come from limited number (18) of refractive indices from literature. The target domain can be easily extended to other material classes with a few literature data. Defining thickness prediction accuracy to be within-10% deviation, thicknessML achieves 92.2% (with a deviation of 3.6%) accuracy with transfer learning compared to 81.8% (with a deviation of 3.6%) 11.7% without (lower mean and larger standard deviation). Experimental validation on six deposited perovskite films also corroborates the efficacy of the proposed workflow by yielding a 10.5% mean absolute percentage error (MAPE).
Bayesian Optimization (BO) machine learning method is increasingly used to guide experimental optimization tasks in materials science. To emulate the large number of input variables and noise-containing results in experimental materials research, we perform batch BO simulation of six design variables with a range of noise levels. Two test cases relevant for materials science problems are examined: a needle-in-a-haystack case (Ackley function) that may be encountered in, e.g., molecule optimizations, and a smooth landscape with a local optimum in addition to the global optimum (Hartmann function) that may be encountered in, e.g., material composition optimization. We show learning curves, performance metrics, and visualization to effectively track the optimization progression and evaluate how the optimization outcomes are affected by noise, batch-picking method, choice of acquisition function, and exploration hyperparameter values. We find that the effects of noise depend on the problem landscape: noise degrades the optimization results of a needle-in-a-haystack search (Ackley) dramatically more. However, with increasing noise, we observe an increasing probability of landing on the local optimum in Hartmann. Therefore, prior knowledge of the problem domain structure and noise level is essential when designing BO for materials research experiments. Synthetic data studies -- with known ground truth and controlled noise levels -- enable us to isolate and evaluate the impact of different batch BO components, {\it e.g.}, acquisition policy, objective metrics, and hyperparameter values, before transitioning to the inherent uncertainties of real experimental systems. The results and methodology of this study will facilitate a greater utilization of BO in guiding experimental materials research, specifically in settings with a large number of design variables to optimize.
Felipe Oviedo, Juan Lavista Ferres, Tonio Buonassisi et al.
While the uptake of data-driven approaches for materials science and chemistry is at an exciting, early stage, to realise the true potential of machine learning models for successful scientific discovery, they must have qualities beyond purely predictive power. The predictions and inner workings of models should provide a certain degree of explainability by human experts, permitting the identification of potential model issues or limitations, building trust on model predictions and unveiling unexpected correlations that may lead to scientific insights. In this work, we summarize applications of interpretability and explainability techniques for materials science and chemistry and discuss how these techniques can improve the outcome of scientific studies. We discuss various challenges for interpretable machine learning in materials science and, more broadly, in scientific settings. In particular, we emphasize the risks of inferring causation or reaching generalization by purely interpreting machine learning models and the need of uncertainty estimates for model explanations. Finally, we showcase a number of exciting developments in other fields that could benefit interpretability in material science and chemistry problems.
While halide perovskites attract significant academic attention, examples of at-scale industrial production are still sparse. In this perspective, we review practical challenges hindering the commercialization of halide perovskites, and discuss how machine-learning (ML) tools could help: (1) active-learning algorithms that blend institutional knowledge and human expertise could help stabilize and rapidly update baseline manufacturing processes; (2) ML-powered metrology, including computer imaging, could help narrow the performance gap between large- and small-area devices; and (3) inference methods could help accelerate root-cause analysis by reconciling multiple data streams and simulations, focusing research effort on areas with highest probability for improvement. We conclude that to satisfy many of these challenges, incremental -- not radical -- adaptations of existing ML and statistical methods are needed. We identify resources to help develop in-house data-science talent, and propose how industry-academic partnerships could help adapt "ready-now" ML tools to specific industry needs, further improve process control by revealing underlying mechanisms, and develop "gamechanger" discovery-oriented algorithms to better navigate vast materials combination spaces and the literature.
Perovskite photovoltaics (PV) have achieved rapid development in the past decade in terms of power conversion efficiency of small-area lab-scale devices; however, successful commercialization still requires further development of low-cost, scalable, and high-throughput manufacturing techniques. One of the critical challenges of developing a new fabrication technique is the high-dimensional parameter space for optimization, but machine learning (ML) can readily be used to accelerate perovskite PV scaling. Herein, we present an ML-guided framework of sequential learning for manufacturing process optimization. We apply our methodology to the Rapid Spray Plasma Processing (RSPP) technique for perovskite thin films in ambient conditions. With a limited experimental budget of screening 100 process conditions, we demonstrated an efficiency improvement to 18.5% as the best-in-our-lab device fabricated by RSPP, and we also experimentally found 10 unique process conditions to produce the top-performing devices of more than 17% efficiency, which is 5 times higher rate of success than the control experiments with pseudo-random Latin hypercube sampling. Our model is enabled by three innovations: (a) flexible knowledge transfer between experimental processes by incorporating data from prior experimental data as a probabilistic constraint; (b) incorporation of both subjective human observations and ML insights when selecting next experiments; (c) adaptive strategy of locating the region of interest using Bayesian optimization first, and then conducting local exploration for high-efficiency devices. Furthermore, in virtual benchmarking, our framework achieves faster improvements with limited experimental budgets than traditional design-of-experiments methods (e.g., one-variable-at-a-time sampling).
Alexander E. Siemenn, Evyatar Shaulsky, Matthew Beveridge et al.
Generating droplets from a continuous stream of fluid requires precise tuning of a device to find optimized control parameter conditions. It is analytically intractable to compute the necessary control parameter values of a droplet-generating device that produces optimized droplets. Furthermore, as the length scale of the fluid flow changes, the formation physics and optimized conditions that induce flow decomposition into droplets also change. Hence, a single proportional integral derivative controller is too inflexible to optimize devices of different length scales or different control parameters, while classification machine learning techniques take days to train and require millions of droplet images. Therefore, the question is posed, can a single method be created that universally optimizes multiple length-scale droplets using only a few data points and is faster than previous approaches? In this paper, a Bayesian optimization and computer vision feedback loop is designed to quickly and reliably discover the control parameter values that generate optimized droplets within different length-scale devices. This method is demonstrated to converge on optimum parameter values using 60 images in only 2.3 hours, 30x faster than previous approaches. Model implementation is demonstrated for two different length-scale devices: a milliscale inkjet device and a microfluidics device.
Qiaohao Liang, Aldair E. Gongora, Zekun Ren et al.
In the field of machine learning (ML) for materials optimization, active learning algorithms, such as Bayesian Optimization (BO), have been leveraged for guiding autonomous and high-throughput experimentation systems. However, very few studies have evaluated the efficiency of BO as a general optimization algorithm across a broad range of experimental materials science domains. In this work, we evaluate the performance of BO algorithms with a collection of surrogate model and acquisition function pairs across five diverse experimental materials systems, namely carbon nanotube polymer blends, silver nanoparticles, lead-halide perovskites, as well as additively manufactured polymer structures and shapes. By defining acceleration and enhancement metrics for general materials optimization objectives, we find that for surrogate model selection, Gaussian Process (GP) with anisotropic kernels (automatic relevance detection, ARD) and Random Forests (RF) have comparable performance and both outperform the commonly used GP without ARD. We discuss the implicit distributional assumptions of RF and GP, and the benefits of using GP with anisotropic kernels in detail. We provide practical insights for experimentalists on surrogate model selection of BO during materials optimization campaigns.
Alexander E. Siemenn, Matthew Beveridge, Tonio Buonassisi et al.
High-performance semiconductor optoelectronics such as perovskites have high-dimensional and vast composition spaces that govern the performance properties of the material. To cost-effectively search these composition spaces, we utilize a high-throughput experimentation method of rapidly printing discrete droplets via inkjet deposition, in which each droplet is comprised of a unique permutation of semiconductor materials. However, inkjet printer systems are not optimized to run high-throughput experimentation on semiconductor materials. Thus, in this work, we develop a computer vision-driven Bayesian optimization framework for optimizing the deposited droplet structures from an inkjet printer such that it is tuned to perform high-throughput experimentation on semiconductor materials. The goal of this framework is to tune to the hardware conditions of the inkjet printer in the shortest amount of time using the fewest number of droplet samples such that we minimize the time and resources spent on setting the system up for material discovery applications. We demonstrate convergence on optimum inkjet hardware conditions in 10 minutes using Bayesian optimization of computer vision-scored droplet structures. We compare our Bayesian optimization results with stochastic gradient descent.
Precise control over dimension of nanocrystals is critical to tune the properties for various applications. However, the traditional control through experimental optimization is slow, tedious and time consuming. Herein a robust deep neural network-based regression algorithm has been developed for precise prediction of length, width, and aspect ratios of semiconductor nanorods (NRs). Given there is limited experimental data available (28 samples), a Synthetic Minority Oversampling Technique for regression (SMOTE-REG) has been employed for the first time for data generation. Deep neural network is further applied to develop regression model which demonstrated the well performed prediction on both the original and generated data with a similar distribution. The prediction model is further validated with additional experimental data, showing accurate prediction results. Additionally, Local Interpretable Model-Agnostic Explanations (LIME) is used to interpret the weight for each variable, which corresponds to its importance towards the target dimension, which is approved to be well correlated well with experimental observations.
Zekun Ren, Siyu Isaac Parker Tian, Juhwan Noh et al.
Realizing general inverse design could greatly accelerate the discovery of new materials with user-defined properties. However, state-of-the-art generative models tend to be limited to a specific composition or crystal structure. Herein, we present a framework capable of general inverse design (not limited to a given set of elements or crystal structures), featuring a generalized invertible representation that encodes crystals in both real and reciprocal space, and a property-structured latent space from a variational autoencoder (VAE). In three design cases, the framework generates 142 new crystals with user-defined formation energies, bandgap, thermoelectric (TE) power factor, and combinations thereof. These generated crystals, absent in the training database, are validated by first-principles calculations. The success rates (number of first-principles-validated target-satisfying crystals/number of designed crystals) ranges between 7.1% and 38.9%. These results represent a significant step toward property-driven general inverse design using generative models, although practical challenges remain when coupled with experimental synthesis.
Jatin N. Kumar, Qianxiao Li, Karen Y. T. Tang et al.
Inverse design is an outstanding challenge in disordered systems with multiple length scales such as polymers, particularly when designing polymers with desired phase behavior. We demonstrate high-accuracy tuning of poly(2-oxazoline) cloud point via machine learning. With a design space of four repeating units and a range of molecular masses, we achieve an accuracy of 4 °C root mean squared error (RMSE) in a temperature range of 24-90 °C, employing gradient boosting with decision trees. The RMSE is >3x better than linear and polynomial regression. We perform inverse design via particle-swarm optimization, predicting and synthesizing 17 polymers with constrained design at 4 target cloud points from 37 to 80 °C. Our approach challenges the status quo in polymer design with a machine learning algorithm, that is capable of fast and systematic discovery of new polymers.
X-ray diffraction (XRD) data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials. We propose a machine-learning-enabled approach to predict crystallographic dimensionality and space group from a limited number of thin-film XRD patterns. We overcome the scarce-data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data. As a test case, 115 thin-film metal halides spanning 3 dimensionalities and 7 space-groups are synthesized and classified. After testing various algorithms, we develop and implement an all convolutional neural network, with cross validated accuracies for dimensionality and space-group classification of 93% and 89%, respectively. We propose average class activation maps, computed from a global average pooling layer, to allow high model interpretability by human experimentalists, elucidating the root causes of misclassification. Finally, we systematically evaluate the maximum XRD pattern step size (data acquisition rate) before loss of predictive accuracy occurs, and determine it to be 0.16°, which enables an XRD pattern to be obtained and classified in 5.5 minutes or less.