One of the main objectives of the Mars Exploration Program is to search for evidence of past or current life on the planet. To achieve this, Mars exploration has been focusing on regions that may have liquid or frozen water. A set of critical areas may have seen cycles of ice thawing in the relatively recent past in response to periodic changes in the obliquity of Mars. In this work, we use convolutional neural networks to detect surface regions containing "Brain Coral" terrain, a landform on Mars whose similarity in morphology and scale to sorted stone circles on Earth suggests that it may have formed as a consequence of freeze/thaw cycles. We use large images (~100-1000 megapixels) from the Mars Reconnaissance Orbiter to search for these landforms at resolutions close to a few tens of centimeters per pixel (~25--50 cm). Over 52,000 images (~28 TB) were searched (~5% of the Martian surface) where we found detections in over 200 images. To expedite the processing we leverage a classifier network (prior to segmentation) in the Fourier domain that can take advantage of JPEG compression by leveraging blocks of coefficients from a discrete cosine transform in lieu of decoding the entire image at the full spatial resolution. The hybrid pipeline approach maintains ~93% accuracy while cutting down on ~95% of the total processing time compared to running the segmentation network at the full resolution on every image. The timely processing of big data sets helps inform mission operations, geologic surveys to prioritize candidate landing sites, avoid hazardous areas, or map the spatial extent of certain terrain. The segmentation masks and source code are available on Github for the community to explore and build upon.
Accelerating compute intensive non-real-time beam-forming algorithms in ultrasound imaging using deep learning architectures has been gaining momentum in the recent past. Nonetheless, the complexity of the state-of-the-art deep learning techniques poses challenges for deployment on resource-constrained edge devices. In this work, we propose a novel vision transformer based tiny beamformer (Tiny-VBF), which works on the raw radio-frequency channel data acquired through single-angle plane wave insonification. The output of our Tiny-VBF provides fast envelope detection requiring very low frame rate, i.e. 0.34 GOPs/Frame for a frame size of 368 x 128 in comparison to the state-of-the-art deep learning models. It also exhibited an 8% increase in contrast and gains of 5% and 33% in axial and lateral resolution respectively when compared to Tiny-CNN on in-vitro dataset. Additionally, our model showed a 4.2% increase in contrast and gains of 4% and 20% in axial and lateral resolution respectively when compared against conventional Delay-and-Sum (DAS) beamformer. We further propose an accelerator architecture and implement our Tiny-VBF model on a Zynq UltraScale+ MPSoC ZCU104 FPGA using a hybrid quantization scheme with 50% less resource consumption compared to the floating-point implementation, while preserving the image quality.
Spiking Neural Networks (SNNs), a novel brain-inspired algorithm, are garnering increased attention for their superior computation and energy efficiency over traditional artificial neural networks (ANNs). To facilitate deployment on memory-constrained devices, numerous studies have explored SNN pruning. However, these efforts are hindered by challenges such as scalability challenges in more complex architectures and accuracy degradation. Amidst these challenges, the Lottery Ticket Hypothesis (LTH) emerges as a promising pruning strategy. It posits that within dense neural networks, there exist winning tickets or subnetworks that are sparser but do not compromise performance. To explore a more structure-sparse and energy-saving model, we investigate the unique synergy of SNNs with LTH and design two novel spiking winning tickets to push the boundaries of sparsity within SNNs. Furthermore, we introduce an innovative algorithm capable of simultaneously identifying both weight and patch-level winning tickets, enabling the achievement of sparser structures without compromising on the final model's performance. Through comprehensive experiments on both RGB-based and event-based datasets, we demonstrate that our spiking lottery ticket achieves comparable or superior performance even when the model structure is extremely sparse.
The rapid increase in the parameters of deep learning models has led to significant costs, challenging computational efficiency and model interpretability. In this paper, we introduce a novel and straightforward neural network pruning framework that incorporates the Gumbel-Softmax technique. This framework enables the simultaneous optimization of a network's weights and topology in an end-to-end process using stochastic gradient descent. Empirical results demonstrate its exceptional compression capability, maintaining high accuracy on the MNIST dataset with only 0.15\% of the original network parameters. Moreover, our framework enhances neural network interpretability, not only by allowing easy extraction of feature importance directly from the pruned network but also by enabling visualization of feature symmetry and the pathways of information propagation from features to outcomes. Although the pruning strategy is learned through deep learning, it is surprisingly intuitive and understandable, focusing on selecting key representative features and exploiting data patterns to achieve extreme sparse pruning. We believe our method opens a promising new avenue for deep learning pruning and the creation of interpretable machine learning systems.
As the popularity of hierarchical point forecast reconciliation methods increases, there is a growing interest in probabilistic forecast reconciliation. Many studies have utilized machine learning or deep learning techniques to implement probabilistic forecasting reconciliation and have made notable progress. However, these methods treat the reconciliation step as a fixed and hard post-processing step, leading to a trade-off between accuracy and coherency. In this paper, we propose a new approach for probabilistic forecast reconciliation. Unlike existing approaches, our proposed approach fuses the prediction step and reconciliation step into a deep learning framework, making the reconciliation step more flexible and soft by introducing the Kullback-Leibler divergence regularization term into the loss function. The approach is evaluated using three hierarchical time series datasets, which shows the advantages of our approach over other probabilistic forecast reconciliation methods.
We review advancements in deep learning techniques for complete intersection Calabi-Yau (CICY) 3- and 4-folds, with the aim of understanding better how to handle algebraic topological data with machine learning. We first discuss methodological aspects and data analysis, before describing neural networks architectures. Then, we describe the state-of-the art accuracy in predicting Hodge numbers. We include new results on extrapolating predictions from low to high Hodge numbers, and conversely.
The proposed framework named IDEAL (Interpretable-by-design DEep learning ALgorithms) recasts the standard supervised classification problem into a function of similarity to a set of prototypes derived from the training data, while taking advantage of existing latent spaces of large neural networks forming so-called Foundation Models (FM). This addresses the issue of explainability (stage B) while retaining the benefits from the tremendous achievements offered by DL models (e.g., visual transformers, ViT) pre-trained on huge data sets such as IG-3.6B + ImageNet-1K or LVD-142M (stage A). We show that one can turn such DL models into conceptually simpler, explainable-through-prototypes ones. The key findings can be summarized as follows: (1) the proposed models are interpretable through prototypes, mitigating the issue of confounded interpretations, (2) the proposed IDEAL framework circumvents the issue of catastrophic forgetting allowing efficient class-incremental learning, and (3) the proposed IDEAL approach demonstrates that ViT architectures narrow the gap between finetuned and non-finetuned models allowing for transfer learning in a fraction of time \textbf{without} finetuning of the feature space on a target dataset with iterative supervised methods.
With the increasing use of deep learning on data collected by non-perfect sensors and in non-perfect environments, the robustness of deep learning systems has become an important issue. A common approach for obtaining robustness to noise has been to train deep learning systems with data augmented with Gaussian noise. In this work, we challenge the common choice of Gaussian noise and explore the possibility of stronger robustness for non-Gaussian impulsive noise, specifically alpha-stable noise. Justified by the Generalized Central Limit Theorem and evidenced by observations in various application areas, alpha-stable noise is widely present in nature. By comparing the testing accuracy of models trained with Gaussian noise and alpha-stable noise on data corrupted by different noise, we find that training with alpha-stable noise is more effective than Gaussian noise, especially when the dataset is corrupted by impulsive noise, thus improving the robustness of the model. The generality of this conclusion is validated through experiments conducted on various deep learning models with image and time series datasets, and other benchmark corrupted datasets. Consequently, we propose a novel data augmentation method that replaces Gaussian noise, which is typically added to the training data, with alpha-stable noise.
Differential Privacy (DP) is a key property to protect data and models from integrity attacks. In the Deep Learning (DL) field, it is commonly implemented through the Differentially Private Stochastic Gradient Descent (DP-SGD). However, when a model is shared or released, there is no way to check whether it is differentially private, that is, it required to trust the model provider. This situation poses a problem when data privacy is mandatory, specially with current data regulations, as the presence of DP can not be certificated consistently by any third party. Thus, we face the challenge of determining whether a DL model has been trained with DP, according to the title question: Can we infer the presence of Differential Privacy in Deep Learning models' weights? Since the DP-SGD significantly changes the training process of a DL model, we hypothesize that DP leaves an imprint in the weights of a DL model, which can be used to predict whether a model has been trained with DP regardless of its architecture and the training dataset. In this paper, we propose to employ the imprint in model weights of using DP to infer the presence of DP training in a DL model. To substantiate our hypothesis, we developed an experimental methodology based on two datasets of weights of DL models, each with models with and without DP training and a meta-classifier to infer whether DP was used in the training process of a DL model, by accessing its weights. We accomplish both, the removal of the requirement of a trusted model provider and a strong foundation for this interesting line of research. Thus, our contribution is an additional layer of security on top of the strict private requirements of DP training in DL models, towards to DL models.
Using autonomous underwater vehicles, or AUVs, has completely changed how we gather data from the ocean floor. AUV innovation has advanced significantly, especially in the analysis of images, due to the increasing need for accurate and efficient seafloor mapping. This blog post provides a detailed summary and comparison of the most current advancements in AUV seafloor image processing. We will go into the realm of undersea technology, covering everything through computer and algorithmic advancements to advances in sensors and cameras. After reading this page through to the end, you will have a solid understanding of the most up-to-date techniques and tools for using AUVs to process seabed photos and how they could further our comprehension of the ocean floor
Pathological alterations in the human vascular system underlie many chronic diseases, such as atherosclerosis and aneurysms. However, manually analyzing diagnostic images of the vascular system, such as computed tomographic angiograms (CTAs) is a time-consuming and tedious process. To address this issue, we propose a deep learning model to segment the vascular system in CTA images of patients undergoing surgery for peripheral arterial disease (PAD). Our study focused on accurately segmenting the vascular system (1) from the descending thoracic aorta to the iliac bifurcation and (2) from the descending thoracic aorta to the knees in CTA images using deep learning techniques. Our approach achieved average Dice accuracies of 93.5% and 80.64% in test dataset for (1) and (2), respectively, highlighting its high accuracy and potential clinical utility. These findings demonstrate the use of deep learning techniques as a valuable tool for medical professionals to analyze the health of the vascular system efficiently and accurately. Please visit the GitHub page for this paper at https://github.com/pip-alireza/TransOnet.
Deep learning-based MRI reconstruction models have achieved superior performance these days. Most recently, diffusion models have shown remarkable performance in image generation, in-painting, super-resolution, image editing and more. As a generalized diffusion model, cold diffusion further broadens the scope and considers models built around arbitrary image transformations such as blurring, down-sampling, etc. In this paper, we propose a k-space cold diffusion model that performs image degradation and restoration in k-space without the need for Gaussian noise. We provide comparisons with multiple deep learning-based MRI reconstruction models and perform tests on a well-known large open-source MRI dataset. Our results show that this novel way of performing degradation can generate high-quality reconstruction images for accelerated MRI.
The notion of group invariance helps neural networks in recognizing patterns and features under geometric transformations. Group convolutional neural networks enhance traditional convolutional neural networks by incorporating group-based geometric structures into their design. This research studies affine invariance on continuous-domain convolutional neural networks. Despite other research considering isometric invariance or similarity invariance, we focus on the full structure of affine transforms generated by the group of all invertible $2 \times 2$ real matrices (generalized linear group $\mathrm{GL}_2(\mathbb{R})$). We introduce a new criterion to assess the invariance of two signals under affine transformations. The input image is embedded into the affine Lie group $G_2 = \mathbb{R}^2 \ltimes \mathrm{GL}_2(\mathbb{R})$ to facilitate group convolution operations that respect affine invariance. Then, we analyze the convolution of embedded signals over $G_2$. In sum, our research could eventually extend the scope of geometrical transformations that usual deep-learning pipelines can handle.
Zenkai is an open-source framework designed to give researchers more control and flexibility over building and training deep learning machines. It does this by dividing the deep learning machine into layers of semi-autonomous learning machines with their own target and learning algorithm. This is to allow researchers greater exploration such as the use of non-differentiable layers or learning algorithms beyond those based on error backpropagation. Backpropagation Rumelhart et al. [1986] has powered deep learning to become one of the most exciting fields of the 21st century. As a result, a large number of software tools have been developed to support efficient implementation and training of neural networks through the use of backpropa- gation. While these have been critical to the success of deep learning, building frameworks around backpropagation can make it challenging to implement solutions that do not adhere to it. Zenkai aims to make it easier to get around these limitations and help researchers more easily explore new frontiers in deep learning that do not strictly adhere to the backpropagation framework.
Regularization is a critical component in deep learning. The most commonly used approach, weight decay, applies a constant penalty coefficient uniformly across all parameters. This may be overly restrictive for some parameters, while insufficient for others. To address this, we present Constrained Parameter Regularization (CPR) as an alternative to traditional weight decay. Unlike the uniform application of a single penalty, CPR enforces an upper bound on a statistical measure, such as the L2-norm, of individual parameter matrices. Consequently, learning becomes a constraint optimization problem, which we tackle using an adaptation of the augmented Lagrangian method. CPR introduces only a minor runtime overhead and only requires setting an upper bound. We propose simple yet efficient mechanisms for initializing this bound, making CPR rely on no hyperparameter or one, akin to weight decay. Our empirical studies on computer vision and language modeling tasks demonstrate CPR's effectiveness. The results show that CPR can outperform traditional weight decay and increase performance in pre-training and fine-tuning.
The volume-corrected mitotic index (M/V-Index) was shown to provide prognostic value in invasive breast carcinomas. However, despite its prognostic significance, it is not established as the standard method for assessing aggressive biological behaviour, due to the high additional workload associated with determining the epithelial proportion. In this work, we show that using a deep learning pipeline solely trained with an annotation-free, immunohistochemistry-based approach, provides accurate estimations of epithelial segmentation in canine breast carcinomas. We compare our automatic framework with the manually annotated M/V-Index in a study with three board-certified pathologists. Our results indicate that the deep learning-based pipeline shows expert-level performance, while providing time efficiency and reproducibility.
Recent advances in deep learning architectures for sequence modeling have not fully transferred to tasks handling time-series from electronic health records. In particular, in problems related to the Intensive Care Unit (ICU), the state-of-the-art remains to tackle sequence classification in a tabular manner with tree-based methods. Recent findings in deep learning for tabular data are now surpassing these classical methods by better handling the severe heterogeneity of data input features. Given the similar level of feature heterogeneity exhibited by ICU time-series and motivated by these findings, we explore these novel methods' impact on clinical sequence modeling tasks. By jointly using such advances in deep learning for tabular data, our primary objective is to underscore the importance of step-wise embeddings in time-series modeling, which remain unexplored in machine learning methods for clinical data. On a variety of clinically relevant tasks from two large-scale ICU datasets, MIMIC-III and HiRID, our work provides an exhaustive analysis of state-of-the-art methods for tabular time-series as time-step embedding models, showing overall performance improvement. In particular, we evidence the importance of feature grouping in clinical time-series, with significant performance gains when considering features within predefined semantic groups in the step-wise embedding module.
Image quality assessment (IQA) plays a critical role in optimizing radiation dose and developing novel medical imaging techniques in computed tomography (CT). Traditional IQA methods relying on hand-crafted features have limitations in summarizing the subjective perceptual experience of image quality. Recent deep learning-based approaches have demonstrated strong modeling capabilities and potential for medical IQA, but challenges remain regarding model generalization and perceptual accuracy. In this work, we propose a multi-scale distributions regression approach to predict quality scores by constraining the output distribution, thereby improving model generalization. Furthermore, we design a dual-branch alignment network to enhance feature extraction capabilities. Additionally, semi-supervised learning is introduced by utilizing pseudo-labels for unlabeled data to guide model training. Extensive qualitative experiments demonstrate the effectiveness of our proposed method for advancing the state-of-the-art in deep learning-based medical IQA. Code is available at: https://github.com/zunzhumu/MD-IQA.
Artificial neural networks open up unprecedented machine learning capabilities at the cost of ever growing computational requirements. Sparsifying the parameters, often achieved through weight pruning, has been identified as a powerful technique to compress the number of model parameters and reduce the computational operations of neural networks. Yet, sparse activations, while omnipresent in both biological neural networks and deep learning systems, have not been fully utilized as a compression technique in deep learning. Moreover, the interaction between sparse activations and weight pruning is not fully understood. In this work, we demonstrate that activity sparsity can compose multiplicatively with parameter sparsity in a recurrent neural network model based on the GRU that is designed to be activity sparse. We achieve up to $20\times$ reduction of computation while maintaining perplexities below $60$ on the Penn Treebank language modeling task. This magnitude of reduction has not been achieved previously with solely sparsely connected LSTMs, and the language modeling performance of our model has not been achieved previously with any sparsely activated recurrent neural networks or spiking neural networks. Neuromorphic computing devices are especially good at taking advantage of the dynamic activity sparsity, and our results provide strong evidence that making deep learning models activity sparse and porting them to neuromorphic devices can be a viable strategy that does not compromise on task performance. Our results also drive further convergence of methods from deep learning and neuromorphic computing for efficient machine learning.
Lattice reduction is a combinatorial optimization problem aimed at finding the most orthogonal basis in a given lattice. The Lenstra-Lenstra-Lov\'asz (LLL) algorithm is the best algorithm in the literature for solving this problem. In light of recent research on algorithm discovery, in this work, we would like to answer this question: is it possible to parametrize the algorithm space for lattice reduction problem with neural networks and find an algorithm without supervised data? Our strategy is to use equivariant and invariant parametrizations and train in a self-supervised way. We design a deep neural model outputting factorized unimodular matrices and train it in a self-supervised manner by penalizing non-orthogonal lattice bases. We incorporate the symmetries of lattice reduction into the model by making it invariant to isometries and scaling of the ambient space and equivariant with respect to the hyperocrahedral group permuting and flipping the lattice basis elements. We show that this approach yields an algorithm with comparable complexity and performance to the LLL algorithm on a set of benchmarks. Additionally, motivated by certain applications for wireless communication, we extend our method to a convolutional architecture which performs joint reduction of spatially-correlated lattices arranged in a grid, thereby amortizing its cost over multiple lattices.