Recent advancements in self-supervised learning have unlocked the potential to harness unlabeled data for auxiliary tasks, facilitating the learning of beneficial priors. This has been particularly advantageous in fields like medical image analysis, where labeled data are scarce. Although effective for classification tasks, this methodology has shown limitations in more complex applications, such as medical image segmentation. In this paper, we introduce Medical imaging Enhanced with Dynamic Self-Adaptive Semantic Segmentation (MedSASS), a dedicated self-supervised framework tailored for medical image segmentation. We evaluate MedSASS against existing state-of-the-art methods across four diverse medical datasets, showcasing its superiority. MedSASS outperforms existing CNN-based self-supervised methods by 3.83% and matches the performance of ViT-based methods. Furthermore, when MedSASS is trained end-to-end, covering both encoder and decoder, it demonstrates significant improvements of 14.4% for CNNs and 6% for ViT-based architectures compared to existing state-of-the-art self-supervised strategies.

Large Language Models(LLMs) have been attracting attention due to a ability called in-context learning(ICL). ICL, without updating the parameters of a LLM, it is possible to achieve highly accurate inference based on rules ``in the context'' by merely inputting a training data into the prompt. Although ICL is a developing field with many unanswered questions, LLMs themselves serves as a inference model, seemingly realizing inference without explicitly indicate ``inductive bias''. On the other hand, a code generation is also a highlighted application of LLMs. The accuracy of code generation has dramatically improved, enabling even non-engineers to generate code to perform the desired tasks by crafting appropriate prompts. In this paper, we propose a novel ``learning'' method called an ``Inductive-Bias Learning (IBL)'', which combines the techniques of ICL and code generation. An idea of IBL is straightforward. Like ICL, IBL inputs a training data into the prompt and outputs a code with a necessary structure for inference (we referred to as ``Code Model'') from a ``contextual understanding''. Despite being a seemingly simple approach, IBL encompasses both a ``property of inference without explicit inductive bias'' inherent in ICL and a ``readability and explainability'' of the code generation. Surprisingly, generated Code Models have been found to achieve predictive accuracy comparable to, and in some cases surpassing, ICL and representative machine learning models. Our IBL code is open source: https://github.com/fuyu-quant/IBLM

We present a new task setting for attribute mining on e-commerce products, serving as a practical solution to extract open-world attributes without extensive human intervention. Our supervision comes from a high-quality seed attribute set bootstrapped from existing resources, and we aim to expand the attribute vocabulary of existing seed types, and also to discover any new attribute types automatically. A new dataset is created to support our setting, and our approach Amacer is proposed specifically to tackle the limited supervision. Especially, given that no direct supervision is available for those unseen new attributes, our novel formulation exploits self-supervised heuristic and unsupervised latent attributes, which attains implicit semantic signals as additional supervision by leveraging product context. Experiments suggest that our approach surpasses various baselines by 12 F1, expanding attributes of existing types significantly by up to 12 times, and discovering values from 39% new types.

For a class of biped robots with impulsive dynamics and a non-empty set of passive gaits (unactuated, periodic motions of the biped model), we present a method for computing continuous families of locally optimal gaits with respect to a class of commonly used energetic cost functions (e.g., the integral of torque-squared). We compute these families using only the passive gaits of the biped, which are globally optimal gaits with respect to these cost functions. Our approach fills in an important gap in the literature when computing a library of locally optimal gaits, which often do not make use of these globally optimal solutions as seed values. We demonstrate our approach on a well-studied two-link biped model.

Neural networks have become popular in many fields of science since they serve as promising, reliable and powerful tools. In this work, we study the effect of data augmentation on the predictive power of neural network models for nuclear physics data. We present two different data augmentation techniques, and we conduct a detailed analysis in terms of different depths, optimizers, activation functions and random seed values to show the success and robustness of the model. Using the experimental uncertainties for data augmentation for the first time, the size of the training data set is artificially boosted and the changes in the root-mean-square error between the model predictions on the test set and the experimental data are investigated. Our results show that the data augmentation decreases the prediction errors, stabilizes the model and prevents overfitting. The extrapolation capabilities of the MLP models are also tested for newly measured nuclei in AME2020 mass table, and it is shown that the predictions are significantly improved by using data augmentation.

Many modern statistical techniques incorporate randomness: simulation, bootstrapping, random forests, and so forth. To use the technique, you need to specify a seed value, which determines pseudorandom numbers that are used in the algorithm. Consequently, the seed value also determines the results of the algorithm. In theory, if you know the seed value and the internal details of the pseudorandom algorithm, then the stream is completely determined, and the results of an algorithm are reproducible. For example, if I publish code for a simulation or bootstrap method in SAS, you can reproduce my computations as long as my program specifies the seed value for every part of the program that uses random numbers.

This tutorial's code is available on Github and its full implementation as well on Google Colab. Towards AI is a community that discusses artificial intelligence, data science, data visualization, deep learning, machine learning, NLP, computer vision, related news, robotics, self-driving cars, programming, technology, and more! Random numbers are everywhere in our lives, whether roulette in the Casino, cryptography, statistical sampling, or as simple as throwing a die gives us a random number between 1 to 6. In this tutorial, we will dive into what pseudorandomness is, its importance in machine learning and data science, and how to create a random number generator to generate pseudorandom numbers in Python using popular libraries. Check out our neural networks from scratch tutorial.

A pseudorandom number generator produces numbers deterministically but they seem aperiodic (random) most of the time for most use-cases. The generator accepts a seed value (ideally a true random number) and starts producing the sequence as a function of this seed and/or a previous number of the sequence. These are Pseudorandom (not truly random) because if seed value is known they can be determined algorithmically. True random numbers are hardware generated or generated from blood volume pulse, atmospheric pressure, thermal noise, quantum phenomenon, etc. There are lots of techniques to generate Pseudorandom numbers, namely: Blum Blum Shub algorithm, Middle-square method, Lagged Fibonacci generator, etc.

In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate for common sequence tagging tasks that the seed value for the random number generator can result in statistically significant (p < 10^-4) differences for state-of-the-art systems. For two recent systems for NER, we observe an absolute difference of one percentage point F1-score depending on the selected seed value, making these systems perceived either as state-of-the-art or mediocre. Instead of publishing and reporting single performance scores, we propose to compare score distributions based on multiple executions. Based on the evaluation of 50.000 LSTM-networks for five sequence tagging tasks, we present network architectures that produce both superior performance as well as are more stable with respect to the remaining hyperparameters.

Two-Class Boosted Decision Tree module creates a machine learning model that is based on the boosted decision trees algorithm. A boosted decision tree is an ensemble learning method in which the second tree corrects for the errors of the first tree, the third tree corrects for the errors of the first and second trees, and so forth. Predictions are based on the entire ensemble of trees together that makes the prediction. Step 1 Add the Boosted Decision Tree module to the experiment. Step 2 Specify how you want the model to be trained, by setting the Create trainer mode option.