January 21, 2018 Vasilis Vryniotis . 1 Comment Deep Learning (the favourite buzzword of late 2010s along with blockchain/bitcoin and Data Science/Machine Learning) has enabled us to do some really cool stuff the last few years. Other than the advances in algorithms (which admittedly are based on ideas already known since 1990s aka “Data Mining era”), the main reasons of its success can be attributed to the availability of large free datasets, the introduction of open-source libraries and the use of GPUs. In this blog post I will focus on the last two and I’ll share with you some tips that I learned the hard way. Why TensorFlow & Keras? TensorFlow is a very popular Deep Learning library developed by Google which allows you to prototype quickly complex networks. It comes with lots of interesting features such as auto-differentiation (which saves you from estimating/coding the gradients of the cost functions) and GPU support (which allows you to get easily a 200x speed improvement using decent hardware). Moreover it offers a Python interface which means that you can prototype quickly without requiring to write C or CUDA code. Admittedly there are lots of other frameworks one can use instead of TensorFlow,...

A new artificial intelligence system ItpCtrl-AI promises to greatly improve chest X-ray diagnostics by offering both interpretability and controllability – addressing the long-standing challenge of AI transparency in medical imaging. Developed by researchers at the University of Arkansas in collaboration with MD Anderson Cancer Center, ItpCtrl-AI models radiologists’ gaze patterns to ensure its decision-making process aligns with human expertise. AI-driven diagnostic tools have demonstrated remarkable accuracy in detecting medical abnormalities, such as fluid accumulation in the lungs, enlarged hearts, and early signs of cancer. However, many of these AI models function as “black boxes,” making it difficult for medical professionals to understand how conclusions are reached. According to Ngan Le, assistant professor of computer science and computer engineering at the University of Arkansas, transparency is critical for the adoption of AI in medicine. “When people understand the reasoning process and limitations behind AI decisions, they are more likely to trust and embrace the technology,” Le said. ItpCtrl-AI, short for interpretable and controllable artificial intelligence, was designed to bridge this gap by replicating how radiologists analyze chest X-rays. Unlike conventional AI systems that simply predict diagnoses, ItpCtrl-AI generates gaze heatmaps – visual representations of the areas radiologists focus on during their...

This article is a cutout of my forthcoming book that you can sign up for here: https://www.danrose.ai/book A significant concept in understanding your data is the concept of Black Swans. The black swan theory was coined by statistician and author of Fooled by Randomness Nassim Nicholas Taleb. A book I can only recommend. For many years it was commonly known that black swans did not exist. As black swans had never been observed, they did not exist in any data. Had you at that time put your bid on the chance that the next swan you saw would then be black, you would probably bet against such an event. It turned out that there were lots of black swans. They just had not been observed yet. They first became so when we discovered Australia, which was full of black swans. In other words, the data only represented the known and observed world and not the actual world.  That is also an excellent time to mention that data is only historical. And as the notion goes in data science, historical data is quite bad, but the best we got. Black Swans are, on an individual level, very rare. The latest Covid pandemic is a...

Powered by metronome.com Welcome Interested in sponsorship opportunities? Join the AI conversation and transform your advertising strategy with AI weekly sponsorship aiweekly.co In the News 9 benefits of AI in 2025 We are living in the era of AI. Since OpenAI launched ChatGPT in late 2022, a wave of new AI tools and technologies has emerged. AI is already changing industries, government operations, and everyday life. As AI continues to improve, its impact will only grow. londondaily.news Sponsor Assembly AI’s billing non-negotiables With just 3 months to switch billing vendors, AssemblyAI had a list of requirements and no time to waste. That list led them to Metronome—the clear winner that ticked all the boxes, and then some. Read the guide that led Assembly AI’s decision to partner with Metronome. Read the guide metronome.com In The News Energy demands from AI datacentres to quadruple by 2030, says report The IEA forecast indicates a sharp rise in the requirements of AI, but said threat to the climate was ‘overstated’ theguardian.com AI avatar generator Synthesia does video footage deal with Shutterstock British startup will license content to train latest model for more ‘human-like performances’ from its avatars theguardian.com OpenAI countersues Elon Musk, calls...

After a post by Andrej Karpathy went viral, “vibe coding” became the buzzword of the year—or at least the first quarter. It means programming exclusively with AI, without looking at or touching the code. If it doesn’t work, you have the AI try again, perhaps with a modified prompt that explains what went wrong. Simon Willison has an excellent blog post about what vibe coding means, when it’s appropriate, and how to do it. While Simon is very positive about vibe coding, he’s frustrated that few of the people who are talking about it have read to the end of Karpathy’s tweet, where he says that vibe coding is most appropriate for weekend projects. Karpathy apparently agrees; he posted this response: …In practice I rarely go full out vibe coding, and more often I still look at the code, I add complexity slowly and I try to learn over time how the pieces work, to ask clarifying questions etc. I’ve been experimenting with vibe coding over the past few months. I’ll start with a disclaimer: While I’ve been programming for a long time, I’m not (and have never been) a professional programmer. My programming consists of “weekend projects” and quick...

Multi-modal large language models (MLLMs) have shown great progress as versatile AI assistants capable of handling diverse visual tasks. However, their deployment as isolated digital entities limits their potential impact. The growing demand to integrate MLLMs into real-world applications like robotics and autonomous vehicles requires complex spatial understanding. Current MLLMs show fundamental spatial reasoning deficiencies, often failing at basic tasks such as distinguishing left from right. While previous research attributes these limitations to insufficient specialized training data and solves them through spatial data incorporation during training, these approaches focus on single-image scenarios, thus restricting the model’s perception to static field-of-view analysis without dynamic information. Several research methods have tried to address spatial understanding limitations in MLLMs. MLLMs incorporate image encoders that convert visual inputs into tokens processed alongside text in the language model’s latent space. Previous research has focused on single-image spatial understanding, evaluating inter-object spatial relations, or spatial recognition. Some benchmarks like BLINK, UniQA-3D, and VSIBench extend beyond single images. Existing improvements of MLLMs for spatial understanding include SpatialVLM, which fine-tunes models on curated spatial datasets, SpatialRGPT, which incorporates mask-based references and depth images, and SpatialPIN, which utilizes specialized perception models without fine-tuning. Researchers from FAIR Meta and the...