# Deep learning Deep learning is a subset of machine learning driven by multilayered neural networks. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Decoding cosmic signals with deep learning and Keras DevFeed: [Decoding cosmic signals with deep learning and Keras]() Original publisher: [Read original article]() Author: Yufeng Guo; Jonas Glombitza, PhD Published: 2026-09-12T11:04:33.891311Z Content type: article Language: en Sources: [Google Developers Blog]() Topics: [Deep learning](), [Keras](), [data]() Tags: [analysis](), [blog-post](), [data](), [deep-learning](), [keras](), [particle-physics](), [physics](), [research]() ### AI overview The article explains how deep learning and Keras can help analyze the enormous, complex datasets produced by astroparticle-physics observatories. These methods may improve instrument sensitivity, reveal hidden patterns, and identify anomalies in signals from cosmic messengers such as photons, neutrinos, and cosmic rays. ### Source excerpt Astroparticle physics sits at the exciting intersection of astrophysics and particle physics and stu... ## System helps humans predict when self-driving cars will make mistakes DevFeed: [System helps humans predict when self-driving cars will make mistakes]() Original publisher: [Read original article]() Author: Adam Zewe | MIT News Published: 2026-09-02T15:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [autonomous vehicles](), [Deep learning](), [Artificial Intelligence](), [Robotics](), [Simulation](), [Computer science]() Tags: [aeronautical-and-astronautical-engineering](), [ai](), [artificial-intelligence](), [autonomous-vehicles](), [computer-science-and-artificial-intelligence-laboratory-csail](), [computer-science-and-technology](), [concept-wrapper-network](), [cw-net](), [deep](), [electrical-engineering-and-computer-science-eecs](), [eoin-kenny](), [human-computer-interaction](), [julie-shah](), [laura-major](), [machine-learning](), [mit-schwarzman-college-of-computing](), [momchil-tomov](), [motional](), [research](), [robotics](), [safety](), [school-of-engineering](), [self-driving](), [self-driving-cars](), [simulation](), [transparency]() ### AI overview MIT and Motional researchers developed CW-Net, a method that translates an autonomous vehicle's deep-learning decisions into understandable concepts. Tests found that the explanations helped safety drivers and nonexpert users better predict vehicle behavior. ### Source excerpt A new method, called CW-Net, translates the reasoning process of an autonomous vehicle's AI system into understandable concepts that explain its behavior. ## Seeing beyond BMI: Estimating cardiometabolic risk with smartphone imagery DevFeed: [Seeing beyond BMI: Estimating cardiometabolic risk with smartphone imagery]() Original publisher: [Read original article]() Published: 2026-08-17T10:34:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Deep neural networks](), [Deep learning](), [Machine learning](), [Google]() Tags: [deep-learning](), [general-science](), [google](), [health](), [health-bioscience](), [machine-intelligence](), [machine-learning](), [monitoring](), [multimodal](), [science]() ### AI overview Google Research presents PhotoScan, a deep learning approach that estimates body composition from smartphone photos and predicts insulin resistance with accuracy comparable to DXA scans in a clinical research setting. The article explains how body-composition measures such as fat distribution and visceral fat may complement wearable data for earlier cardiometabolic risk assessment. ### Source excerpt General Science ## From Campus to Community Part Two: The Researcher Exodus DevFeed: [From Campus to Community Part Two: The Researcher Exodus]() Original publisher: [Read original article]() Author: Nithya Ruff Published: 2026-07-13T14:07:27Z Content type: opinion Language: en Sources: [Linux Foundation - Blog]() Topics: [Artificial Intelligence](), [linux foundation](), [Open Source](), [Deep learning](), [Computer science](), [Hardware](), [Robotics]() Tags: [ai](), [computer-science](), [deep-learning](), [hardware](), [linux-foundation](), [open-source](), [robotics]() ### AI overview The second part of a Linux Foundation series argues that AI researchers leaving universities for industry jobs, combined with limited academic access to computing resources, is weakening open-source development and academic research. It cites faculty departure data and examples from Carnegie Mellon and other research communities. ### Source excerpt This is a series from Linux Foundation Board Chair, Nithya Ruff. Part One can be found here. ## From pixels to planning: Earth AI for nature restoration DevFeed: [From pixels to planning: Earth AI for nature restoration]() Original publisher: [Read original article]() Published: 2026-06-16T17:30:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Earth AI](), [Artificial Intelligence](), [dataset](), [Deep learning](), [Google](), [data]() Tags: [ai](), [climate-sustainability](), [data](), [deep-learning](), [earth-ai](), [google](), [machine-intelligence](), [open-source-models-datasets](), [research](), [resource](), [sustainability](), [uk](), [vector]() ### AI overview Google Research describes a high-resolution deep learning approach that converts pixel-based maps of fine-scale ecological features into a vectorized dataset. The resource is intended to support nature restoration, carbon accounting, and biodiversity efforts across working landscapes in the UK while considering food security. ### Source excerpt Climate & Sustainability ## Towards passive heart health monitoring via smartphone camera DevFeed: [Towards passive heart health monitoring via smartphone camera]() Original publisher: [Read original article]() Published: 2026-06-04T19:47:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Monitoring](), [webcam](), [dataset](), [Deep learning](), [Google](), [Ground truth / benchmark quality]() Tags: [deep-learning](), [devices](), [google](), [health](), [health-bioscience](), [heart-rate-monitoring](), [human-computer-interaction-and-visualization](), [machine-intelligence](), [model](), [monitoring](), [publication](), [research](), [resource](), [smartphones]() ### AI overview Google Research presents PHRM, a research system that passively estimates heart rate and resting heart rate from facial video captured by a smartphone's front-facing camera during everyday use. The system applies deep learning to video recorded after face unlock events and reports accuracy comparable to electrocardiogram-derived ground truth and wearable trackers. The publication also releases a large, diverse smartphone-video dataset and the pre-trained PHRM-mini model for qualified researchers. ### Source excerpt Health & Bioscience ## Distilling Long-Tail User Behavior into Scalable Embeddings for Job Search DevFeed: [Distilling Long-Tail User Behavior into Scalable Embeddings for Job Search]() Original publisher: [Read original article]() Author: Marsan Ma Published: 2026-06-03T23:28:10Z Content type: article Language: en Sources: [Indeed]() Topics: [recommendation systems](), [Embeddings](), [Deep learning](), [Latency](), [Job]() Tags: [big-data](), [data-science](), [deep-learning](), [embeddings](), [engineering](), [feature-store](), [job-search](), [latency](), [machine-learning](), [performance](), [ranking]() ### AI overview Indeed describes a user behavior modeling system for job search that learns from long-term user histories offline, distills them into fixed-length embeddings, and serves them through a feature store for use by online ranking and recommendation models. The approach is designed to preserve rich behavioral signals while meeting latency and cost constraints. ### Source excerpt Authors : Marsan Ma, Nikhil Lopes, Raj Amrit, Hong Lu, Dipankar Biswas, Trent KyonoLeadership: Iris Wang, Madhu Kurup Recommendation and ranking systems power many of the most important experiences on large internet platforms. Yet the models that run in production are rarely the largest models we can train. They are usually compact, latency-sensitive supervised models [...] ## Where wild things roam: Identifying wildlife with SpeciesNet DevFeed: [Where wild things roam: Identifying wildlife with SpeciesNet]() Original publisher: [Read original article]() Published: 2026-03-06T17:59:38Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Earth AI](), [Artificial Intelligence](), [Google](), [Open Source](), [Deep learning](), [Data analysis](), [data](), [migration]() Tags: [ai](), [ai-models](), [analysis](), [climate-sustainability](), [data](), [datasets](), [deep-learning](), [earth-ai](), [generative-ai](), [google](), [migration](), [open-source](), [open-source-models-datasets](), [sustainability]() ### AI overview Google Research describes SpeciesNet, an open-source AI model that identifies nearly 2,500 animal categories in camera-trap images. Trained on 65 million labelled images, it is being used by research groups worldwide to support wildlife monitoring, conservation, and analysis of animal populations and patterns. ### Source excerpt Climate & Sustainability ## Sequential Attention: Making AI models leaner and faster without sacrificing accuracy DevFeed: [Sequential Attention: Making AI models leaner and faster without sacrificing accuracy]() Original publisher: [Read original article]() Published: 2026-02-04T15:14:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Algorithms & Theory](), [Optimization](), [Programming](), [Machine learning](), [Deep learning](), [Google]() Tags: [ai](), [algorithms](), [algorithms-theory](), [deep-learning](), [features](), [google](), [machine-learning](), [optimization](), [research](), [scalability](), [training]() ### AI overview Google Research presents Sequential Attention, a greedy and adaptive subset-selection method for making large-scale machine-learning and deep-learning models more efficient. The approach selects useful components such as features, layers, blocks, embedding chunks, or weight entries during a single training run, reducing redundancy while preserving accuracy and limiting additional training cost. ### Source excerpt Algorithms & Theory ## Unlocking health insights: Estimating advanced walking metrics with smartwatches DevFeed: [Unlocking health insights: Estimating advanced walking metrics with smartwatches]() Original publisher: [Read original article]() Published: 2026-01-15T22:56:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Deep learning](), [model architecture](), [data](), [Google]() Tags: [architecture](), [data](), [deep-learning](), [evaluation](), [google](), [health](), [health-bioscience](), [human-computer-interaction-and-visualization](), [model](), [performance](), [portable](), [smartphones](), [validation]() ### AI overview Google researchers report a large-scale validation study showing that consumer smartwatches can accurately estimate comprehensive spatio-temporal gait metrics, including walking speed, step length, and double support time. They describe a multi-output deep learning model using a temporal convolutional network and smartwatch inertial sensor data, with performance comparable to smartphone-based methods. ### Source excerpt Health & Bioscience ## Easily Build and Share ROCm Kernels with Hugging Face DevFeed: [Easily Build and Share ROCm Kernels with Hugging Face]() Original publisher: [Read original article]() Author: Abdennacer Badaoui; Daniel Huang; colorswind; Zesen Liu Published: 2025-11-17T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [kernels](), [rocm](), [hugging face](), [PyTorch](), [Deep learning](), [Open Source](), [benchmarking](), [CUDA]() Tags: [amd](), [architectures](), [best-practices](), [build](), [building](), [compiler](), [compute](), [core](), [cuda](), [deep-learning](), [deployment](), [developer](), [gpu](), [hardware](), [hugging-face](), [innovation](), [kernels](), [open-source](), [pytorch](), [rocm]() ### AI overview This tutorial explains how to build, test, package, deploy, and share ROCm-compatible GPU kernels with Hugging Face's kernels library and kernel-builder. It focuses on integrating kernels with PyTorch and optimizing them for AMD GPUs, using a high-performance FP8 GEMM kernel for the AMD Instinct MI300X as an example. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Differentially private machine learning at scale with JAX-Privacy DevFeed: [Differentially private machine learning at scale with JAX-Privacy]() Original publisher: [Read original article]() Published: 2025-11-12T15:32:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Machine Learning & Artificial Intelligence](), [Algorithms, Complexity](), [Deep learning](), [distributed-training](), [data](), [Google](), [High-Performance Computing](), [Programming]() Tags: [algorithms](), [algorithms-theory](), [data](), [deep-learning](), [distributed-training](), [google](), [high-performance-computing](), [libraries](), [machine-learning](), [release](), [research](), [responsible-ai](), [scalability](), [security-privacy-and-abuse-prevention](), [training]() ### AI overview Google announces JAX-Privacy 1.0, a library for differentially private machine learning built on JAX. The release is intended to help researchers and developers implement, audit, and scale private training workflows for deep learning models using large datasets and distributed training. ### Source excerpt Algorithms & Theory ## Forecasting the future of forests with AI: From counting losses to predicting risk DevFeed: [Forecasting the future of forests with AI: From counting losses to predicting risk]() Original publisher: [Read original article]() Published: 2025-11-05T15:41:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Artificial Intelligence](), [Benchmark](), [Deep learning](), [Google](), [dataset](), [data](), [Monitoring]() Tags: [ai](), [benchmark](), [climate-sustainability](), [data](), [deep-learning](), [evaluation](), [global](), [google](), [models](), [monitoring](), [open-source-models-datasets](), [research](), [sustainability]() ### AI overview Google Research and Google DeepMind introduce ForestCast, a deep learning-powered benchmark and public dataset for forecasting deforestation risk. The approach uses satellite data to predict future risk consistently across regions, addressing limitations of backward-looking forest-loss monitoring and patchy, outdated input maps. The released input, training, and evaluation data are intended to support reproducibility and further research. ### Source excerpt Climate & Sustainability ## AI for Food Allergies DevFeed: [AI for Food Allergies]() Original publisher: [Read original article]() Author: Ludovico Comito; Antonis Vozikis; Vaibhav Pandey; Kisejjere Rashid Published: 2025-10-16T22:38:11Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Artificial Intelligence](), [Bioinformatics](), [Machine learning](), [Deep learning]() Tags: [ai](), [deep-learning](), [machine-learning](), [models](), [research](), [science]() ### AI overview The article introduces the AI for Food Allergies project, a community-driven research effort exploring how artificial intelligence can advance food allergy research. It describes the use of bioinformatics, machine learning, and deep learning models to analyze proteins and amino-acid sequences, identify allergen-related patterns, and improve prediction of allergenicity. The supplied text ends mid-sentence. ### Source excerpt So, what can we do about it? In recent years, biomedical research has made several remarkable advances: from experimental vaccines and desensitization-based immunotherapies to improved diagnostic tools capable of identifying specific allergen sensitivities with unprecedented precision. These developments are pointing us in the right direction toward building long-term immune tolerance, but we're not quite there yet. ## How I learn about generative AI DevFeed: [How I learn about generative AI]() Original publisher: [Read original article]() Author: Pamela Fox (noreply@blogger.com) Published: 2025-08-19T05:59:00Z Content type: opinion Language: en Sources: [Pamela Fox]() Topics: [Generative AI](), [AI Engineering](), [LLM evaluation / benchmarking](), [web applications](), [LLMs](), [Retrieval Augmented Generation (RAG)](), [Python](), [PyTorch](), [AI-assisted coding](), [Transformer](), [Deep learning](), [Language models]() Tags: [ai](), [ai-assisted-coding](), [ai-engineering](), [deep-learning](), [evaluation](), [generative-ai](), [llm](), [openai](), [python](), [pytorch](), [transformer-architecture]() ### AI overview The author shares the books, videos, newsletters, communities, and blogs they used to learn generative AI. The resources cover AI engineering, building large language models with Python and PyTorch, neural networks, model evaluation, retrieval-augmented generation, and AI-assisted coding. ### Source excerpt I do not consider myself an expert in generative AI, but I now know enough to build full-stack web applications on top of generative AI models, evaluate the quality of those applications, and decide whether new models or frameworks will be useful. These are the resources that I personally used for getting up to speed with generative AI. AI foundation Let's start first with the long-form content: books and videos that gave me a more solid foundation. AI Engineering By Chip Huyen This book is a fantastic high-level overview of the AI Engineering industry from an experienced ML researcher. I recommend that everybody read this book at some point in your learning journey. Despite Chip's background in ML, the book is very accessible - no ML background is needed, though a bit of programming with LLMs would be a good warm-up for the book. I loved how Chip included both research and industry insights, and her focus on the need for evaluation in the later chapters. Please, read this book! Build a Large Language Model By Sebastian Raschka This book is a deep dive into building LLMs from scratch using Python and Pytorch, and includes a GitHub repository with runnable code. I found it helpful to see that LLMs are all about matrix manipulation, and to wrap my head around how the different layers in the LLM architecture map to matrices. I recommend it to Python developers who want to understand concepts like the transformer architecture, or even just common LLM parameters like temperature and top p. If you're new to Pytorch, this book thankfully includes an intro in the appendix, but I also liked the Deep Learning with PyTorch book. Zero to Hero By Andrej Karpathy This video series builds neural networks from scratch, entirely in Jupyter notebooks. Andrej is a fantastic teacher, and has a great way of explaining complex topics. Admittedly, I have not watched every video from start to finish, but every time I do watch a video from Andrej, I learn so much. Andrej also gives great ta ## Touchpad Digit Recognition Based on ESP-DL DevFeed: [Touchpad Digit Recognition Based on ESP-DL]() Original publisher: [Read original article]() Author: John Lee Published: 2025-06-18T00:00:00Z Content type: tutorial Language: en Sources: [Blog on Developer Portal]() Topics: [ESP32-S3](), [ESP32-P4](), [Embedded Systems](), [Deep learning](), [Jetson](), [Artificial Intelligence](), [quantization](), [Inference](), [Code]() Tags: [ai](), [applications](), [blog](), [c-plus-plus](), [deep-learning](), [devices](), [edge-computing](), [embedded-systems](), [esp-dl](), [esp32](), [esp32-p4](), [esp32-s3](), [inference](), [neural-networks](), [quantization](), [recognition]() ### AI overview This tutorial demonstrates touchpad-based digit recognition on ESP32-S3 and ESP32-P4 using ESP-DL. It covers touch-data collection and preprocessing, lightweight CNN design, model training and evaluation, quantization, and C++ implementation for model loading and inference. ### Source excerpt This article demonstrates how to implement a touchpad-based digit recognition system using ESP-DL on ESP32 series chips. It covers the complete workflow from data collection and preprocessing to model training, quantization, and deployment, showcasing ESP-DL's capabilities in edge AI applications. ## TPU vs. GPU: Differences in Performance, Applications, Cost, and Ecosystem DevFeed: [TPU vs. GPU: Differences in Performance, Applications, Cost, and Ecosystem]() Original publisher: [Read original article]() Published: 2025-03-11T23:10:26Z Content type: comparison Language: en Sources: [Learn on Tailscale]() Topics: [GPU](), [Artificial Intelligence](), [AI Infrastructure](), [Deep learning](), [Google](), [Google Cloud Platform (GCP)](), [High-Performance Computing](), [Neural Network]() Tags: [ai](), [applications](), [deep-learning](), [efficiency](), [google](), [google-cloud-platform](), [gpu](), [high-performance-computing](), [speed](), [tpu](), [vs]() ### AI overview This comparison explains how Google TPUs and GPUs differ in AI processing. TPUs are designed for high-speed, low-precision deep-learning computation on Google Cloud, while GPUs provide more flexible parallel processing and broad framework compatibility. ### Source excerpt Two key players dominate the efficiency and speed of AI applications: the Graphics Processing Unit (GPU) and the Tensor Processing Unit (TPU). Both have their strengths and weaknesses. ## Developing a High-Accuracy Fall Detection Device Using Raspberry Pi and Transformer Models DevFeed: [Developing a High-Accuracy Fall Detection Device Using Raspberry Pi and Transformer Models]() Original publisher: [Read original article]() Author: Ivan Ursul Published: 2024-11-16T00:00:00Z Content type: article Language: en Sources: [Ivan Ursul]() Topics: [Raspberry Pi](), [Transformer](), [Deep learning](), [Development](), [Hardware](), [data](), [data-processing](), [Single Board Computer](), [Arduino]() Tags: [ai](), [deep-learning](), [elderly-care](), [fall-detection](), [false-positives](), [hardware](), [java](), [machine-learning](), [migrations](), [models](), [mongodb](), [motion-detection](), [prototype](), [raspberry-pi](), [real-time](), [research](), [single-board-computer](), [transformers]() ### AI overview This project describes a Raspberry Pi Zero 2W fall-detection device using accelerometer, gyroscope, and barometric pressure sensors. It processes fall and Activities of Daily Living data with Transformer-based deep learning models, with a focus on real-time detection and minimizing false positives. ### Source excerpt Your browser does not support the audio element. ** Dive into an AI-generated podcast where two virtual hosts discuss the key findings and implications of the featured article and its groundbreaking research." The prototype with the cover removed Falls are a significant concern for the elderly po... ## Deep Learning Frameworks for Beginners: A Comparison of TensorFlow vs. PyTorch vs. Keras DevFeed: [Deep Learning Frameworks for Beginners: A Comparison of TensorFlow vs. PyTorch vs. Keras]() Original publisher: [Read original article]() Author: admin Published: 2024-05-14T10:48:43Z Content type: comparison Language: en Sources: [Posts on Chris Banes]() Topics: [Deep learning](), [Frameworks](), [Tensorflow](), [PyTorch]() Tags: [ai](), [comparison](), [deep-learning](), [frameworks](), [pytorch](), [tensorflow](), [uncategorized](), [vs]() ### AI overview This beginner-oriented comparison introduces deep learning frameworks and discusses TensorFlow, PyTorch, and Keras. It explains how frameworks support the design, training, and testing of deep learning models, with particular attention to TensorFlow's scalability, mobile deployment through TensorFlow Lite, and production pipelines through TFX. ### Source excerpt Have you ever wondered how computers can recognize faces, understand your voice commands, or even beat you at a game of chess? That's deep learning in action! Deep learning is a powerful part of artificial intelligence (AI) that teaches computers to learn from data, just like humans do. Deep learning frameworks are handy tools, enabling [...] ## AI News Roundup: GPT-5 Rumors, Deep Learning, Meta Glasses, ChatGPT Memory, and Safari Search DevFeed: [AI News Roundup: GPT-5 Rumors, Deep Learning, Meta Glasses, ChatGPT Memory, and Safari Search]() Original publisher: [Read original article]() Author: Pradeep Kumar Published: 2024-05-06T16:16:23Z Content type: article Language: en Sources: [Air Around AI]() Topics: [Artificial Intelligence](), [Large Language Model](), [Deep learning](), [ChatGPT](), [OpenAI](), [Meta](), [browser]() Tags: [ai](), [browser](), [chatgpt](), [deep-learning](), [gpt](), [llms](), [meta](), [openai]() ### AI overview A roundup of AI-related developments and resources, including speculation about a new chatbot possibly being GPT-5, MIT's Introduction to Deep Learning course, comparisons of large language models, Meta's AI-powered Ray-Ban glasses, ChatGPT memory features, and Safari's Intelligent Search. ### Source excerpt gpt-2, intro to deep learning by MIT, Meta Glasses, Intelligent Search in Safari ## Health-specific embedding tools for dermatology and pathology DevFeed: [Health-specific embedding tools for dermatology and pathology]() Original publisher: [Read original article]() Author: Google AI (noreply@blogger.com) Published: 2024-03-08T19:33:00Z Content type: release Language: en Sources: [Google Research]() Topics: [Medical imaging](), [Embeddings](), [Deep learning](), [Machine learning](), [Google]() Tags: [computer-vision](), [deep-learning](), [embedding](), [google](), [health](), [image-classification](), [medical-imaging](), [product](), [release]() ### AI overview Google Research announces Derm Foundation and Path Foundation, two domain-specific embedding tools for research in dermatology and digital pathology. The tools convert medical images into specialized numerical vectors that researchers can use to develop models for downstream applications. ### Source excerpt Posted by Dave Steiner, Clinical Research Scientist, Google Health, and Rory Pilgrim, Product Manager, Google Research There's a worldwide shortage of access to medical imaging expert interpretation across specialties including radiology, dermatology and pathology. Machine learning (ML) technology can help ease this burden by powering tools that enable doctors to interpret these images more accurately and efficiently. However, the development and implementation of such ML tools are often limited by the availability of high-quality data, ML expertise, and computational resources. One way to catalyze the use of ML for medical imaging is via domain-specific models that utilize deep learning (DL) to capture the information in medical images as compressed numerical vectors (called embeddings). These embeddings represent a type of pre-learned understanding of the important features in an image. Identifying patterns in the embeddings reduces the amount of data, expertise, and compute needed to train performant models as compared to working with high-dimensional data, such as images, directly. Indeed, these embeddings can be used to perform a variety of downstream tasks within the specialized domain (see animated graphic below). This framework of leveraging pre-learned understanding to solve related tasks is similar to that of a seasoned guitar player quickly learning a new song by ear. Because the guitar player has already built up a foundation of skill and understanding, they can quickly pick up the patterns and groove of a new song. Path Foundation is used to convert a small dataset of (image, label) pairs into (embedding, label) pairs. These pairs can then be used to train a task-specific classifier using a linear probe, (i.e., a lightweight linear classifier) as represented in this graphic, or other types of models using the embeddings as input. Once the linear probe is trained, it can be used to make predictions on embeddings from new images. These predictions can be ## A decoder-only foundation model for time-series forecasting DevFeed: [A decoder-only foundation model for time-series forecasting]() Original publisher: [Read original article]() Author: Google AI (noreply@blogger.com) Published: 2024-02-02T19:07:00Z Content type: article Language: en Sources: [Google Research]() Topics: [Time Series](), [foundation-models](), [Google](), [Deep learning]() Tags: [deep-learning](), [forecasting](), [google](), [google-cloud-platform](), [machine-learning](), [model](), [time-series]() ### AI overview Google Research introduces TimesFM, a decoder-only foundation model for time-series forecasting. The model is pretrained on 100 billion real-world time-points and is reported to provide zero-shot forecasts on unseen datasets across domains and temporal granularities, with 200 million parameters. ### Source excerpt Posted by Rajat Sen and Yichen Zhou, Google Research Time-series forecasting is ubiquitous in various domains, such as retail, finance, manufacturing, healthcare and natural sciences. In retail use cases, for example, it has been observed that improving demand forecasting accuracy can meaningfully reduce inventory costs and increase revenue. Deep learning (DL) models have emerged as a popular approach for forecasting rich, multivariate, time-series data because they have proven to perform well in a variety of settings (e.g., DL models performed well in the M5 competition). At the same time, there has been rapid progress in large foundation language models used for natural language processing (NLP) tasks, such as translation, retrieval-augmented generation, and code completion. These models are trained on massive amounts of textual data derived from a variety of sources like common crawl and open-source code that allows them to identify patterns in languages. This makes them very powerful zero-shot tools; for instance, when paired with retrieval, they can answer questions about and summarize current events. Despite DL-based forecasters largely outperforming traditional methods and progress being made in reducing training and inference costs, they face challenges: most DL architectures require long and involved training and validation cycles before a customer can test the model on a new time-series. A foundation model for time-series forecasting, in contrast, can provide decent out-of-the-box forecasts on unseen time-series data with no additional training, enabling users to focus on refining forecasts for the actual downstream task like retail demand planning. To that end, in "A decoder-only foundation model for time-series forecasting", we introduce TimesFM, a single forecasting model pre-trained on a large time-series corpus of 100 billion real world time-points. Compared to the latest large language models (LLMs), TimesFM is much smaller (200M parameters), yet we ## Intervening on early readouts for mitigating spurious features and simplicity bias DevFeed: [Intervening on early readouts for mitigating spurious features and simplicity bias]() Original publisher: [Read original article]() Author: Google AI (noreply@blogger.com) Published: 2024-02-02T17:49:00Z Content type: article Language: en Sources: [Google Research]() Topics: [AI Research](), [Deep learning](), [responsible-ai](), [generalization in machine learning](), [Model Development](), [Training AI Models]() Tags: [bias](), [dataset](), [deep-learning](), [icml](), [machine-learning](), [ml-fairness](), [research](), [responsible-ai](), [supervised-learning](), [training]() ### AI overview Google Research describes methods for detecting and reducing spurious features and simplicity bias in deep learning models. Early readouts expose confidently wrong predictions associated with spurious features, while feature forgetting helps models identify more predictive features and generalize to unseen domains. ### Source excerpt Posted by Rishabh Tiwari, Pre-doctoral Researcher, and Pradeep Shenoy, Research Scientist, Google Research Machine learning models in the real world are often trained on limited data that may contain unintended statistical biases. For example, in the CELEBA celebrity image dataset, a disproportionate number of female celebrities have blond hair, leading to classifiers incorrectly predicting "blond" as the hair color for most female faces -- here, gender is a spurious feature for predicting hair color. Such unfair biases could have significant consequences in critical applications such as medical diagnosis. Surprisingly, recent work has also discovered an inherent tendency of deep networks to amplify such statistical biases, through the so-called simplicity bias of deep learning. This bias is the tendency of deep networks to identify weakly predictive features early in the training, and continue to anchor on these features, failing to identify more complex and potentially more accurate features. With the above in mind, we propose simple and effective fixes to this dual challenge of spurious features and simplicity bias by applying early readouts and feature forgetting. First, in "Using Early Readouts to Mediate Featural Bias in Distillation", we show that making predictions from early layers of a deep network (referred to as "early readouts") can automatically signal issues with the quality of the learned representations. In particular, these predictions are more often wrong, and more confidently wrong, when the network is relying on spurious features. We use this erroneous confidence to improve outcomes in model distillation, a setting where a larger "teacher" model guides the training of a smaller "student" model. Then in "Overcoming Simplicity Bias in Deep Networks using a Feature Sieve", we intervene directly on these indicator signals by making the network "forget" the problematic features and consequently look for better, more predictive features. This substanti ## A clustering-based approach to create deep learning datasets in a day DevFeed: [A clustering-based approach to create deep learning datasets in a day]() Original publisher: [Read original article]() Author: Roland Meertens Published: 2023-11-28T17:33:30Z Content type: article Language: en Sources: [Bumble Tech]() Topics: [dataset](), [Computer vision](), [Deep learning](), [foundation-models](), [Fine-tuning](), [Inference]() Tags: [clustering](), [computer-vision](), [data-science](), [dataset](), [deep-learning](), [fine-tuning](), [inference](), [machine-learning](), [models](), [retrieval](), [zero-shot]() ### AI overview The article discusses the cost and time involved in creating labeled computer vision datasets. It considers zero-shot learning and foundational models such as GPT-3 and CLIP for data retrieval, while noting that some use cases still require fine-tuning on task-specific data. ### Source excerpt A clustering-based approach to create deep learning datasets in a day Introduction Understanding what's happening in an image is both an important task, as well as a costly one. In the last few years, the field of computer vision has greatly accelerated due to the advances in neural networks. At Bumble Inc., we see potential value in computer vision for a variety of use cases, such as improving the safety of our platform and providing our members with a better user experience. The most common way to train these neural networks is by showing it many images with the corresponding label. Unfortunately, this can be a costly task. Not only does one need to build and train the model, one also wants to do hyperparameter search over multiple configurations of possible networks, and -- of course -- one needs to find or build a dataset suitable for the task at hand. Building the dataset is both the most important task, as well as a very time consuming one. Gathering data, setting up labelling requirements, and of course the labelling itself all take a lot of time and money. This normally leads to trade-offs, by choosing either to build only a small dataset, or by trying to fit existing datasets into your specific use-case. One alternative is of course to not build a dataset at all, to instead use zero-shot learning for your use case. I argued in the past that this is unreasonably effective, and allows you to test your use-case before even training a model. When using zero-shot learning one predicts labels without explicitly training on the classes you are trying to learn. One example of this can be achieved by using the CLIP model, which is trained to have a strong association between text and images. By looking at the distance between the description of your class and the image you can run inference without training anything. However, there are some use cases where we need the strongest possible model by fine-tuning it to our specific data. Using foundational models for data s [Next page]()