整流的线性单元目前是深度卷积神经网络中的最先进的激活功能。为了对抗Relu的垂死神经元问题，我们提出了参数分层线性单元（PVLU），其增加了具有培训系数的正弦函数来relu。随着在整个真实域的非线性和非零梯度引入非线性和非零梯度，PVLU在转移学习的背景下实施时作为微调的机制。在简单的非转移顺序CNN上，PVLU取代允许的相对误差减少16.3％和11.3％（无且数据增强）在CIFAR-100上。 PVLU也在转移学习模型上进行测试。 VGG-16和VGG-19分别在CREU与PVLU取代后，在CIFAR-10分别体验了9.5％和10.7％的相对误差。当在高斯过滤的CiFar-10图像上进行培训时，VGG型号将注意类似的改进。最值得注意的是，使用PVLU的微调允许在CIFAR数据集上的近最先进的剩余神经网络架构上的相对误差减少和超过10％。

Foundation models are redefining how AI systems are built. Practitioners now follow a standard procedure to build their machine learning solutions: download a copy of a foundation model, and fine-tune it using some in-house data about the target task of interest. Consequently, the Internet is swarmed by a handful of foundation models fine-tuned on many diverse tasks. Yet, these individual fine-tunings often lack strong generalization and exist in isolation without benefiting from each other. In our opinion, this is a missed opportunity, as these specialized models contain diverse features. Based on this insight, we propose model recycling, a simple strategy that leverages multiple fine-tunings of the same foundation model on diverse auxiliary tasks, and repurposes them as rich and diverse initializations for the target task. Specifically, model recycling fine-tunes in parallel each specialized model on the target task, and then averages the weights of all target fine-tunings into a final model. Empirically, we show that model recycling maximizes model diversity by benefiting from diverse auxiliary tasks, and achieves a new state of the art on the reference DomainBed benchmark for out-of-distribution generalization. Looking forward, model recycling is a contribution to the emerging paradigm of updatable machine learning where, akin to open-source software development, the community collaborates to incrementally and reliably update machine learning models.

To build general robotic agents that can operate in many environments, it is often imperative for the robot to collect experience in the real world. However, this is often not feasible due to safety, time, and hardware restrictions. We thus propose leveraging the next best thing as real-world experience: internet videos of humans using their hands. Visual priors, such as visual features, are often learned from videos, but we believe that more information from videos can be utilized as a stronger prior. We build a learning algorithm, VideoDex, that leverages visual, action, and physical priors from human video datasets to guide robot behavior. These actions and physical priors in the neural network dictate the typical human behavior for a particular robot task. We test our approach on a robot arm and dexterous hand-based system and show strong results on various manipulation tasks, outperforming various state-of-the-art methods. Videos at https://video-dex.github.io

Recently, automated co-design of machine learning (ML) models and accelerator architectures has attracted significant attention from both the industry and academia. However, most co-design frameworks either explore a limited search space or employ suboptimal exploration techniques for simultaneous design decision investigations of the ML model and the accelerator. Furthermore, training the ML model and simulating the accelerator performance is computationally expensive. To address these limitations, this work proposes a novel neural architecture and hardware accelerator co-design framework, called CODEBench. It is composed of two new benchmarking sub-frameworks, CNNBench and AccelBench, which explore expanded design spaces of convolutional neural networks (CNNs) and CNN accelerators. CNNBench leverages an advanced search technique, BOSHNAS, to efficiently train a neural heteroscedastic surrogate model to converge to an optimal CNN architecture by employing second-order gradients. AccelBench performs cycle-accurate simulations for a diverse set of accelerator architectures in a vast design space. With the proposed co-design method, called BOSHCODE, our best CNN-accelerator pair achieves 1.4% higher accuracy on the CIFAR-10 dataset compared to the state-of-the-art pair, while enabling 59.1% lower latency and 60.8% lower energy consumption. On the ImageNet dataset, it achieves 3.7% higher Top1 accuracy at 43.8% lower latency and 11.2% lower energy consumption. CODEBench outperforms the state-of-the-art framework, i.e., Auto-NBA, by achieving 1.5% higher accuracy and 34.7x higher throughput, while enabling 11.0x lower energy-delay product (EDP) and 4.0x lower chip area on CIFAR-10.

Current approaches for fixing systematic problems in NLP models (e.g. regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In contrast, humans often provide corrections to each other through natural language. Taking inspiration from this, we explore natural language patches -- declarative statements that allow developers to provide corrective feedback at the right level of abstraction, either overriding the model (``if a review gives 2 stars, the sentiment is negative'') or providing additional information the model may lack (``if something is described as the bomb, then it is good''). We model the task of determining if a patch applies separately from the task of integrating patch information, and show that with a small amount of synthetic data, we can teach models to effectively use real patches on real data -- 1 to 7 patches improve accuracy by ~1-4 accuracy points on different slices of a sentiment analysis dataset, and F1 by 7 points on a relation extraction dataset. Finally, we show that finetuning on as many as 100 labeled examples may be needed to match the performance of a small set of language patches.

The goal of autonomous vehicles is to navigate public roads safely and comfortably. To enforce safety, traditional planning approaches rely on handcrafted rules to generate trajectories. Machine learning-based systems, on the other hand, scale with data and are able to learn more complex behaviors. However, they often ignore that agents and self-driving vehicle trajectory distributions can be leveraged to improve safety. In this paper, we propose modeling a distribution over multiple future trajectories for both the self-driving vehicle and other road agents, using a unified neural network architecture for prediction and planning. During inference, we select the planning trajectory that minimizes a cost taking into account safety and the predicted probabilities. Our approach does not depend on any rule-based planners for trajectory generation or optimization, improves with more training data and is simple to implement. We extensively evaluate our method through a realistic simulator and show that the predicted trajectory distribution corresponds to different driving profiles. We also successfully deploy it on a self-driving vehicle on urban public roads, confirming that it drives safely without compromising comfort. The code for training and testing our model on a public prediction dataset and the video of the road test are available at https://woven.mobi/safepathnet

When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems like human languages? There is an apparent tension between compositional accounts of human language understanding, which are based on a restricted bottom-up computational process, and the enormous success of neural models like transformers, which can route information arbitrarily between different parts of their input. One possibility is that these models, while extremely flexible in principle, in practice learn to interpret language hierarchically, ultimately building sentence representations close to those predictable by a bottom-up, tree-structured model. To evaluate this possibility, we describe an unsupervised and parameter-free method to \emph{functionally project} the behavior of any transformer into the space of tree-structured networks. Given an input sentence, we produce a binary tree that approximates the transformer's representation-building process and a score that captures how "tree-like" the transformer's behavior is on the input. While calculation of this score does not require training any additional models, it provably upper-bounds the fit between a transformer and any tree-structured approximation. Using this method, we show that transformers for three different tasks become more tree-like over the course of training, in some cases unsupervisedly recovering the same trees as supervised parsers. These trees, in turn, are predictive of model behavior, with more tree-like models generalizing better on tests of compositional generalization.

Climate change is expected to aggravate wildfire activity through the exacerbation of fire weather. Improving our capabilities to anticipate wildfires on a global scale is of uttermost importance for mitigating their negative effects. In this work, we create a global fire dataset and demonstrate a prototype for predicting the presence of global burned areas on a sub-seasonal scale with the use of segmentation deep learning models. Particularly, we present an open-access global analysis-ready datacube, which contains a variety of variables related to the seasonal and sub-seasonal fire drivers (climate, vegetation, oceanic indices, human-related variables), as well as the historical burned areas and wildfire emissions for 2001-2021. We train a deep learning model, which treats global wildfire forecasting as an image segmentation task and skillfully predicts the presence of burned areas 8, 16, 32 and 64 days ahead of time. Our work motivates the use of deep learning for global burned area forecasting and paves the way towards improved anticipation of global wildfire patterns.

Running machine learning inference on tiny devices, known as TinyML, is an emerging research area. This task requires generating inference code that uses memory frugally, a task that standard ML frameworks are ill-suited for. A deployment framework for TinyML must be a) parametric in the number representation to take advantage of the emerging representations like posits, b) carefully assign high-precision to a few tensors so that most tensors can be kept in low-precision while still maintaining model accuracy, and c) avoid memory fragmentation. We describe MinUn, the first TinyML framework that holistically addresses these issues to generate efficient code for ARM microcontrollers (e.g., Arduino Uno, Due and STM32H747) that outperforms the prior TinyML frameworks.

State-of-the-art algorithms for Approximate Nearest Neighbor Search (ANNS) such as DiskANN, FAISS-IVF, and HNSW build data dependent indices that offer substantially better accuracy and search efficiency over data-agnostic indices by overfitting to the index data distribution. When the query data is drawn from a different distribution - e.g., when index represents image embeddings and query represents textual embeddings - such algorithms lose much of this performance advantage. On a variety of datasets, for a fixed recall target, latency is worse by an order of magnitude or more for Out-Of-Distribution (OOD) queries as compared to In-Distribution (ID) queries. The question we address in this work is whether ANNS algorithms can be made efficient for OOD queries if the index construction is given access to a small sample set of these queries. We answer positively by presenting OOD-DiskANN, which uses a sparing sample (1% of index set size) of OOD queries, and provides up to 40% improvement in mean query latency over SoTA algorithms of a similar memory footprint. OOD-DiskANN is scalable and has the efficiency of graph-based ANNS indices. Some of our contributions can improve query efficiency for ID queries as well.