DreamerV3 is a state-of-the-art online model-based reinforcement learning (MBRL) algorithm known for remarkable sample efficiency. Concurrently, Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to Multi-Layer Perceptrons (MLPs), offering superior parameter efficiency and interpretability. To mitigate KANs' computational overhead, variants like FastKAN leverage Radial Basis Functions (RBFs) to accelerate inference. In this work, we investigate integrating KAN architectures into the DreamerV3 framework. We introduce KAN-Dreamer, replacing specific MLP and convolutional components of DreamerV3 with KAN and FastKAN layers. To ensure efficiency within the JAX-based World Model, we implement a tailored, fully vectorized version with simplified grid management. We structure our investigation into three subsystems: Visual Perception, Latent Prediction, and Behavior Learning. Empirical evaluations on the DeepMind Control Suite (walker_walk) analyze sample efficiency, training time, and asymptotic performance. Experimental results demonstrate that utilizing our adapted FastKAN as a drop-in replacement for the Reward and Continue predictors yields performance on par with the original MLP-based architecture, maintaining parity in both sample efficiency and training speed. This report serves as a preliminary study for future developments in KAN-based world models.

Summary This paper presents a framework for implementing different sparse attention mechanisms by regularizing the max operator using convex functions. As a result, softmax and sparsemax are derived as special cases of this framework. Furthermore, two new sparse attention mechanisms are introduced that allow the model to learn to pay the same attention to contiguous spans. My concerns are regarding to the motivation of interpretability, as well as the baseline attention models. However, the paper is very well presented and the framework is a notable contribution that I believe will be useful for researchers working with attention mechanisms.

When we work on a machine learning project, quite often we need to experiment with multiple alternatives. Some features in Python allows us to try out different options without much effort. In this tutorial, we are going to see some tips to make our experiments faster. This is a typical machine learning project workflow. We have a stage of preprocessing of data, then training a model, and afterwards, evaluate our result. But in each step, we may want to try something different.

Fashion-MNIST is a dataset of Zalando's article images consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28 28 grayscale image, associated with a label from 10 classes. They intend Fashion-MNIST to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms. It shares the same image size and structure of training and testing splits. The original MNIST dataset contains a lot of handwritten digits.

Here's a situation every PyCaret user is familiar with: after selecting a promising model or two from compare_models(), it's time to tune its hyperparameters to squeeze out all of the model's potential with tune_model(). By default, tune_model() uses the tried and tested RandomizedSearchCV from scikit-learn. However, not everyone knows about the various advanced options tune_model()provides. In this post, I will show you how easy it is to use other state-of-the-art algorithms with PyCaret thanks to tune-sklearn, a drop-in replacement for scikit-learn's model selection module with cutting edge hyperparameter tuning techniques. I'll also report results from a series of benchmarks, showing how tune-sklearn is able to easily improve classification model performance.

Here's a situation every PyCaret user is familiar with: after selecting a promising model or two from compare_models(), it's time to tune its hyperparameters to squeeze out all of the model's potential with tune_model(). By default, tune_model() uses the tried and tested RandomizedSearchCV from scikit-learn. However, not everyone knows about the various advanced options tune_model()provides. In this post, I will show you how easy it is to use other state-of-the-art algorithms with PyCaret thanks to tune-sklearn, a drop-in replacement for scikit-learn's model selection module with cutting edge hyperparameter tuning techniques. I'll also report results from a series of benchmarks, showing how tune-sklearn is able to easily improve classification model performance.

"Light," a former camera company has announced a new depth sensor that could be a game changer, upending LIDAR and computer vision based depth measurement, by producing a combination RGB image and depth map with ranges out to an astonishing 1000 meters. Presuming it works as promised and can be delivered at scale, this is astonishing news. Some of you will know Light as a company that made a computational camera with 16 lenses at 3 different focal lengths. Combining the images let them produce a high resolution image with an adjustable depth of field, hoping to get SLR quality in a flat box. The tested their first product, and while interesting, it was not ready for prime-time. They later got money from Softbank.

It is often infeasible or impossible to obtain ground truth labels for medical data. To circumvent this, one may build rule-based or other expert-knowledge driven labelers to ingest data and yield silver labels absent any ground-truth training data. One popular such labeler is CheXpert (Irvin et al., 2019), a labeler that produces diagnostic labels for chest X-ray radiology reports. CheXpert is very useful, but is relatively computationally slow, especially when integrated with end-to-end neural pipelines, is non-differentiable so can't be used in any applications that require gradients to flow through the labeler, and does not yield probabilistic outputs, which limits our ability to improve the quality of the silver labeler through techniques such as active learning. In this work, we solve all three of these problems with CheXpert, a BERTbased, highfidelity approximation to CheXpert. CheXpert achieves 99.81% parity with CheXpert, which means it can be reliably used as a drop-in replacement for CheXpert, all while being significantly faster, fully differentiable, and probabilistic in output. Error analysis of CheXpert also demonstrates that CheXpert has a tendency to actually correct errors in the CheXpert labels, with CheXpert labels being more often preferred by a clinician over CheXpert labels (when they disagree) on all but one disease task. To further demonstrate the utility of these advantages in this model, we conduct a proof-of-concept active learning study, demonstrating we can improve accuracy on an expert labeled random subset of report sentences by approximately 8% over raw, unaltered CheXpert by using one-iteration of active-learning inspired retraining. These findings suggest that simple techniques in co-learning and active learning can yield high-quality labelers under minimal, and controllable human labeling demands.

ReLU is widely seen as the default choice for activation functions in neural networks. However, there are cases where more complicated functions are required. In particular, recurrent neural networks (such as LSTMs) make extensive use of both hyperbolic tangent and sigmoid functions. These functions are expensive to compute. We used function approximation techniques to develop replacements for these functions and evaluated them empirically on three popular network configurations. We find safe approximations that yield a 10% to 37% improvement in training times on the CPU. These approximations were suitable for all cases we considered and we believe are appropriate replacements for all networks using these activation functions. We also develop ranged approximations which only apply in some cases due to restrictions on their input domain. Our ranged approximations yield a performance improvement of 20% to 53% in network training time. Our functions also match or considerably out perform the ad-hoc approximations used in Theano and the implementation of Word2Vec.

In this paper, we disseminate a new handwritten digits-dataset, termed Kannada-MNIST, for the Kannada script, that can potentially serve as a direct drop-in replacement for the original MNIST dataset. In addition to this dataset, we disseminate an additional real world handwritten dataset (with $10k$ images), which we term as the Dig-MNIST dataset that can serve as an out-of-domain test dataset. We also duly open source all the code as well as the raw scanned images along with the scanner settings so that researchers who want to try out different signal processing pipelines can perform end-to-end comparisons. We provide high level morphological comparisons with the MNIST dataset and provide baselines accuracies for the dataset disseminated. The initial baselines obtained using an oft-used CNN architecture ($96.8\%$ for the main test-set and $76.1\%$ for the Dig-MNIST test-set) indicate that these datasets do provide a sterner challenge with regards to generalizability than MNIST or the KMNIST datasets. We also hope this dissemination will spur the creation of similar datasets for all the languages that use different symbols for the numeral digits.