Loading…
Topic
617 posts about Machine Learning. Every summary links to the original.
See the idea
A walkthrough of how a 3D CT model turns a voxel volume into a structured diagnostic report: isotropic resampling, 3D patch tokens, spatial encoding, and language-model reasoning.
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Newest first
Streamlit enables developers to create interactive web demonstrations and visualizations for machine learning models and datasets. In an illustrative text completion interface recreating Write with Transformer, UI components such as text areas, sidebars, number inputs, and continuous sliders collect user text and inference hyperparameters. For data inspection, the streaming feature in Hugging Face Datasets loads large corpora directly into memory without requiring complete local downloads, integrating with pandas, matplotlib, and seaborn for tabular and chart rendering. Deploying these interactive applications to Hugging Face Spaces involves uploading the code files while defining dependencies inside a requirements.txt file. Matching local Streamlit versions ensures consistent runtime execution when hosting models and datasets online.
Demonstrating machine learning projects to the community requires accessible hosting and minimal interface boilerplate. Gradio integrates directly with the Hugging Face Hub and its underlying Inference API, enabling developers to load models using repository identifiers and launch interactive interfaces with a few lines of code. Hugging Face Spaces provides a free hosting environment where users select Gradio as the SDK, commit an app.py script, and deploy live web demonstrations for frameworks like Transformers, spaCy, SpeechBrain, and Asteroid. For complex workflows, developers can chain multiple models sequentially via Gradio Series or host custom checkpoints directly when models lack native Inference API support.
Hugging Face released several major updates across its ecosystem, expanding its public Hub repository to over 16,000 models. Platform additions include Spaces for deploying Gradio and Streamlit demo applications, automatic TensorBoard instances, and evaluation metric tracking integrated with Papers With Code leaderboards. The Transformers library gained JAX/Flax support across more than 5,000 models, improved TensorFlow implementations, and introduced the transformers.onnx export module for model conversion. In research, the BigScience project completed large-scale training of a 13-billion-parameter English decoder model on Jean Zay, while the DeDLOC method enabled training the sahajBERT Bengali model without HPC infrastructure. Accepted conference papers detailed the Datasets library, prompt data-point equivalence, prompt-based fine-tuning heuristics, and block pruning techniques that reduced BERT size by 74 percent.
Hugging Face launched its Hardware Partner Program at the 2021 AI Hardware Summit to offer device-optimized models and software integrations. As a founding member of the program, Graphcore collaborated with Hugging Face to optimize Transformer models for its Intelligence Processing Unit (IPU). Graphcore IPUs use a massively parallel MIMD architecture with on-die ultra-high bandwidth memory designed for AI workloads featuring fine-grained parallelism, low precision arithmetic, and sparsity. Through Hugging Face's open-source Optimum toolkit, developers will receive plug-and-play access to certified, hardware-optimized models across vision, speech, translation, and text generation. Graphcore's Poplar SDK integrates with PyTorch, TensorFlow, Docker, and Kubernetes, simplifying the process of porting workloads to IPU-POD datacenter compute systems.
Running Transformer models fast and efficiently at production scale presents a significant challenge due to the complex compatibility between model architectures, acceleration techniques like quantization or sparsity, and specific silicon hardware features. Hugging Face introduced Optimum, an open-source library built to abstract hardware acceleration complexity and optimize training and inference on target devices through direct collaborations with hardware partners. Using quantization as a primary example, engineering teams often struggle with eager-mode model graph modifications, kernel compatibility checks, calibration parameter tuning, and acceptable accuracy loss trade-offs. Optimum addresses these challenges by integrating tools such as Intel Neural Compressor, which supports post-training quantization, quantization-aware training, and dynamic quantization driven by user-defined YAML configurations. Through these hardware-tailored integrations, the library aims to democratize production performance and reduce the aggregate energy consumed by machine learning workloads.
Shopify revisited product categorization as its platform expanded to millions of merchants selling billions of products across diverse industries. The model uses product titles, descriptions, types, vendors, collections, tags, and images, converting them into embeddings with Multilingual BERT and MobileNet-V2 before hierarchical classification across the seven-level Google Product Taxonomy. Each taxonomy level is treated as a separate multi-class task, with parent predictions fed into child predictions and weighted losses combined during training; confidence thresholds filter predictions at each level. The upgraded system increased leaf precision by 8% while almost doubling coverage, although thresholds require balancing accuracy, coverage, merchant experience, and performance in sensitive categories, and future work includes addressing data imbalance and adding merchant-level features.
The article presents a five-step workflow for deciding when and how to build machine learning products in a business setting. It recommends delaying machine learning for new products, establishing data-collection foundations, and testing simple heuristics as baselines before investing in a model. For an initial model, teams should favor simple algorithms, limited feature sets, and off-the-shelf solutions where appropriate, then measure business-aligned impact before optimizing. The workflow also calls for planned model iteration and explicit comparison with existing versions, while accounting for prediction stability when changes could affect user trust. The authors say they used these practices at Shopify to help build and scale machine learning products and to productionize models intended to drive impact.
Supabase announced the winners and runners-up for its inaugural open-source hackathon after concluding deliberations across a larger-than-expected pool of entries. Top entries included Work From, an employee schedule tracking application, and Fireplace, a video streaming platform that leverages Supabase Storage to synchronize playback events across multiple viewers. Additional recognized projects encompassed Feature.so for modular application component management, Flutter Add-ons for telemetry and crash reporting, and Peckish Peach, which uses machine learning to generate recipes from input ingredients. All submitted projects remain fully open source for community inspection, contribution, and forking. Gold and silver prize winners receive custom limited-edition Supabase apparel, while every hackathon participant receives a participation prize.
Grab's KartaView platform collects geotagged street imagery across over 100 countries, requiring automated obfuscation of faces and licence plates to protect personal privacy. Because off-the-shelf solutions struggled with diverse global environments and equirectangular 360-degree camera formats, Grab built a custom machine learning pipeline. The system projects varied image formats into standardized planar views, applies a YOLOv4 object detection model to locate target regions, and transforms bounding coordinates back to the original imagery for blurring. Training the detector required iterative dataset updates to accommodate edge cases like face masks and mirror reflections, paired with offline view splitting and oversampling of scarce large bounding boxes. Assessments confirmed that obfuscating these regions had minimal negative impact on downstream map feature extraction services.
Pretraining state-of-the-art Transformer language models typically requires vast computing resources and expensive hardware clusters that are inaccessible to many researchers. Standard distributed deep learning struggles over public Internet infrastructure because consumer connections suffer from limited bandwidth, dynamic peer disconnections, and restrictive firewalls. To resolve these networking bottlenecks, Distributed Deep Learning in Open Collaborations (DeDLOC) introduces an adaptive training framework that accumulates massive batch sizes across heterogeneous volunteer devices before applying optimizer updates. The framework splits gradient vectors dynamically based on participant connection speeds and allows firewalled nodes to contribute data without performing aggregation. In a practical deployment with 40 volunteers, the 18-million-parameter sahajBERT model achieved Bengali downstream benchmark performance comparable to much larger multilingual models trained on dedicated supercomputers.
Hugging Face has integrated spaCy pipelines into the Hugging Face Hub to simplify the distribution, testing, and deployment of natural language processing models across the community. More than 60 canonical models from the spaCy 3.1 release are hosted in the spaCy organization, alongside discoverable community pipelines. Users can package and upload models directly through the command line using the spacy-huggingface-hub extension, which auto-generates required metadata and model cards. Hosted pipelines offer direct pip installation from live wheel URLs, interactive browser exploration, and production-ready HTTP endpoints through the Inference API. The platform provides immediate interactive widget support for named entity recognition components, with upcoming support planned for text classification and part-of-speech tagging pipelines.
Hugging Face and Amazon introduced an inference solution integrating Hugging Face Transformers with Amazon SageMaker. The SageMaker Hugging Face Inference Toolkit and specialized Deep Learning Containers enable deployment of trained models or publicly available Hub models to managed production endpoints. Users configure endpoints with minimal code using the SageMaker Python SDK, standard pipelines, or custom inference scripts that override default behaviors. The architecture supports models stored in Amazon S3 as well as direct references via HF_MODEL_ID and HF_TASK environment variables. Deployments benefit from native AWS infrastructure features, including built-in monitoring, Identity and Access Management permission controls, and Virtual Private Cloud connectivity.
Grab transitioned from voice hotlines and third-party tools to an in-house native chat support system integrated into their CRM. The team validated the platform through an MVP and user shadowing to address session disconnections, agent context switching, and routing bottlenecks. To optimize support operations at scale, they introduced dynamic queue limits based on Little's law, machine learning autocomplete suggestions for agents, and duration timers with visual nudges. These enhancements reduced chat waiting times by 30%, unresponsive users by 7%, and overall chat handling duration by 22%.
Sentence Transformers has collaborated with the Hugging Face Hub as part of its v2 release to make sentence, paragraph, and image embedding models readily accessible. The Hub now hosts over 90 pretrained models supporting more than 100 languages for use cases like semantic search and multilingual zero-shot classification. Alongside direct model loading in minimal code, the platform provides interactive Hub widgets for feature extraction and sentence similarity computation. Developers can execute inference programmatically through Inference API endpoints. Additionally, the library supports direct model uploading to the Hub via save_to_hub, which automatically generates a model card detailing layer architecture and dual usage with Sentence Transformers and Transformers.
Limited labeled data often prevents machine learning models from achieving high performance during traditional fine-tuning. Few-shot learning addresses this hurdle in natural language processing by supplying a short task description and a few demonstration examples at inference time. EleutherAI developed GPT-Neo, an open transformer-based model trained on the Pile dataset, which can execute few-shot tasks via the Hugging Face Accelerated Inference API. Compared to larger models like GPT-3, the 2.7B parameter version of GPT-Neo requires three to four examples alongside tuned hyperparameters like temperature and stopping sequences to generate accurate completions. Because few-shot learning relies heavily on pre-trained associations, careful output monitoring and human feedback mechanisms remain necessary to prevent automated bias.
The Hugging Face Model Hub hosts more than 10,000 user-submitted machine learning models spanning natural language processing, image classification, and audio processing. Machine learning developers increasingly need to demo models to interdisciplinary collaborators or non-programmers to uncover biases and failure points. The Gradio 2.0 library enables users to create graphical user interfaces and load almost any Hugging Face model using a single line of code. By default, these interfaces query Hugging Face's hosted Inference API without requiring an API key, though users can also run computations locally via the transformers library. Gradio interfaces can be customized through the Interface class and composed to load multiple models in parallel or chain them in series.
Scaling BERT-like model inference on CPUs presents practical deployment challenges as transformer architectures proliferate in production environments. Using a reproducible Hydra-based benchmarking framework, inference workloads were evaluated on an Amazon Web Services c5.metal instance featuring an Intel Xeon Platinum 8275 processor with AVX512 and VNNI support. Out-of-the-box evaluations showed PyTorch 1.8.1 delivering lower latency than Google TensorFlow 2.4.0, likely due to PyTorch relying on OpenMP and Intel MKL/oneDNN rather than Eigen. Implementing multiple inference streams by pinning parallel model instances to dedicated CPU cores yielded near-linear throughput scaling. Matching instance core allocations to specific problem sizes also demonstrated that smaller workloads can achieve optimal latency on fewer cores, enabling up to a sixfold reduction in cloud compute costs.
Agent typing time represented a large portion of Grab's chat support journey, and 85% of messages were still free typed because agents customized static templates to fit their personal style. To accelerate typing across multilingual markets without robotic templates, Grab built SmartChat, a machine learning feature that provides contextual sentence completion. The team opted for a lightweight seq2seq architecture using single-layered GRU encoder-decoders in TensorFlow instead of bulky attention models to keep model latency under 100ms. The user interface was implemented in React using a content-editable div with inline typeahead suggestions activated via keyboard shortcuts.
🤗 Accelerate enables PyTorch developers to execute raw training loops across CPUs, multi-GPU setups, and TPUs with minimal boilerplate modifications. Standard distributed training typically demands manual device assignments, DistributedSampler configurations, and divergent code paths that break single-device portability. By wrapping models, optimizers, and dataloaders through a unified prepare call, Accelerate automatically manages hardware placement, mixed precision operations, and sampler batch slicing without requiring custom distributed samplers. Distributed evaluation is streamlined using a gather utility that consolidates prediction tensors across active worker processes. Furthermore, a dedicated command-line interface provides an interactive questionnaire to store runtime configuration defaults and orchestrate local or AWS SageMaker runs.
Hugging Face and Amazon SageMaker introduced optimized Deep Learning Containers alongside a SageMaker Python SDK estimator to streamline distributed transformer model training. This workflow demonstrates fine-tuning the 400-million-parameter facebook/bart-large-cnn model for dialogue summarization on the 16,000-conversation samsum dataset. Using SageMaker Data Parallelism enabled in the distribution configuration, training executes across two ml.p3dn.24xlarge compute instances equipped with sixteen total GPUs and a cumulative batch size of 64. The HuggingFace estimator pulls the run_summarization.py script directly from GitHub, enables mixed precision with fp16, and tracks evaluation performance through ROUGE scores. Following completion, the unzipped model artifacts and a generated model card are pushed to the Hugging Face Hub using the huggingface_hub library for hosted inference.
The best engineering reads, once a week.
