Code repository to accompany the O'Reilly book: "Strengthening Deep Neural Networks: Making AI Less Susceptible to Adversarial Trickery" (⭐ 57)
Knowledge editing techniques promise to implant new factual knowledge into large language models (LLMs). But do LLMs really believe these facts? We develop a framework to measure belief depth and use it to evaluate the success of knowledge editing te...
Restoring ancient text using deep learning: a case study on Greek epigraphy. (⭐ 230)
Deep Learning model to segment tissues from histopathology images (⭐ 0)
The author intends to provide you with a beautiful, elegant, user-friendly cookbook for mathematics in Snapshot Compressive Imaging (SCI). Currently, the cookbook is composed of introduction, conventional optimization, and deep equilibrium models. Th...
Feb 18, 2026 · Employee safety is a top priority at Newell Brands. Over the past year, we maintained the programs that have allowed us to achieve a world-class safety record while deepening our training …
Each year, underwater remotely operated vehicles (ROVs) collect thousands of hours of video of unexplored ocean habitats revealing a plethora of information regarding biodiversity on Earth. However, fully utilizing this information remains a challeng...
Python package of computational models relevant to invertebrate processing, from the environment to sensor responses and to deeper neural responses in the invertebrate brain. (⭐ 3)
Deep learning models for skin disease classification require large, diverse, and well-annotated datasets. However, such resources are often limited due to privacy concerns, high annotation costs, and insufficient demographic representation. While tex...
Skin cancer detection using Dermatological images and Deep learning (⭐ 15)
Artificial intelligence (AI) algorithms using deep learning have advanced the classification of skin disease images; however these algorithms have been mostly applied "in silico" and not validated clinically. Most dermatology AI algorithms perform bi...
With the widespread application of artificial intelligence (AI), particularly deep learning (DL) and vision large language models (VLLMs), in skin disease diagnosis, the need for interpretability becomes crucial. However, existing dermatology dataset...
In recent years, deep learning (DL) has shown great potential in the field of dermatological image analysis. However, existing datasets in this domain have significant limitations, including a small number of image samples, limited disease conditions...
We explore deep Reinforcement Learning(RL) algorithms for scalping trading and knew that there is no appropriate trading gym and agent examples. Thus we propose gym and agent like Open AI gym in finance. Not only that, we introduce new RL framework b...
Joe Pater's target article calls for greater interaction between neural network research and linguistics. I expand on this call and show how such interaction can benefit both fields. Linguists can contribute to research on neural networks for languag...
There are many applications scenarios for which the computational performance and memory footprint of the prediction phase of Deep Neural Networks (DNNs) needs to be optimized. Binary Neural Networks (BDNNs) have been shown to be an effective way of...
Drawing on 1,178 safety and reliability papers from 9,439 generative AI papers (January 2020 - March 2025), we compare research outputs of leading AI companies (Anthropic, Google DeepMind, Meta, Microsoft, and OpenAI) and AI universities (CMU, MIT, N...
Feb 18, 2026 · Employee safety is a top priority at Newell Brands. Over the past year, we maintained the programs that have allowed us to achieve a world-class safety record while deepening our training …
Boosting your Web Services of Deep Learning Applications. (⭐ 1244)
Previous work has shown the potential of deep learning to predict renal obstruction using kidney ultrasound images. However, these image-based classifiers have been trained with the goal of single-visit inference in mind. We compare methods from vide...