# Keras Keras is a multi-backend deep learning framework for building and training machine-learning models. 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... ## How Keras 3 Helped Modernise Expedia Group's Lodging Ranking Stack DevFeed: [How Keras 3 Helped Modernise Expedia Group's Lodging Ranking Stack]() Original publisher: [Read original article]() Author: Conor Worthington Published: 2026-08-11T11:01:02Z Content type: article Language: en Sources: [Expedia]() Topics: [Keras](), [recommendation systems](), [Latency](), [Inference Performance](), [Machine learning]() Tags: [data-science](), [features](), [framework](), [improvements](), [inference](), [keras](), [latency](), [llms](), [machine-learning](), [mixture-of-experts](), [model-training](), [neural-networks](), [ranking](), [recommendation-system]() ### AI overview Expedia Group describes modernising its lodging-ranking stack around Keras 3. The changes included rewriting parts of its pipelines, making model training 30% faster and reducing P99 inference latency by two-thirds. The article discusses limitations of the previous Keras 2, eager-training and combined-serving setup, along with the use of newer APIs and accelerator-oriented optimisations. ### Source excerpt Expedia Group Technology -- DataWhat happened when we treated a framework migration as an architecture modernisation -- and cut P99 inference latency by two-thirdsSt Paul's and millennium bridge, London Expedia Group™ has always been a market leader in providing personalised search experiences for travellers. As our ranking models evolved, we saw an opportunity not just to migrate to Keras 3, but to modernise the broader stack around it so we can better serve travellers. This led us to rewrite key parts of our pipelines that made model training 30% faster and cut P99 inference latency by two-thirds. Our main focus in this blog is to discuss our improvements to lodging ranking -- our service which handles users' search requests and returns a personalised property ranking on top of a lightweight candidate generator. This service is frequently retrained to improve customer experience as we get new signals over time. Example of personalised lodging ranking on Expedia search result page for a London search As such, our velocity to make changes needs to be fast, but more importantly we need to be able to build models which are state-of-the-art, enabling customers to easily find and book the most relevant property for their trip. The problem with Keras 2, eager training and combined serving The challenge was not that the old stack was broken. It was that it had gradually become a limiting factor. On the training side, we were carrying dependencies on older components and missing out on modern Keras APIs, new optimisers, new layers and cleaner support for accelerator-oriented training. On the serving side, we had a path that was simple and operationally familiar, but not especially well suited to aggressively optimised inference for heavier ranking architectures. This blockage on utilising new layers and optimisers has become more pronounced as LLMs see blistering amounts of innovation. Naturally, these new features are only available in Keras 3 or as separate backends from ou ## Gesture Recognition Based on TFLite DevFeed: [Gesture Recognition Based on TFLite]() Original publisher: [Read original article]() Author: John Lee Published: 2026-04-10T00:00:00Z Content type: tutorial Language: en Sources: [Blog on Developer Portal]() Topics: [TensorFlow Lite](), [Espressif](), [model-deployment](), [Tensorflow](), [Keras](), [On-device AI]() Tags: [ai](), [blog](), [deep-learning](), [deployment](), [development-board](), [edge-ai](), [edge-computing](), [esp-idf](), [espressif](), [how-to](), [inference](), [keras](), [model-deployment](), [model-training](), [tensorflow-lite]() ### AI overview This tutorial demonstrates gesture recognition on Espressif SoCs using TensorFlow Lite Micro. It covers data collection, model training, conversion for TFLite Micro, and deployment with C++ code for model loading, preprocessing, and inference. ### Source excerpt This article demonstrates how to implement gesture recognition using TensorFlow Lite Micro on Espressif SoCs. It covers the complete workflow from data collection and model training to model deployment, showcasing TensorFlow Lite Micro's applications in edge AI. ## What's new in TensorFlow 2.19 DevFeed: [What's new in TensorFlow 2.19]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2025-03-13T16:00:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [Tensorflow](), [LiteRT](), [releases](), [API](), [C++](), [Release notes](), [Keras](), [migration]() Tags: [2025](), [announcement](), [api](), [c-plus-plus](), [keras](), [libentensorflow](), [litert](), [migration-guide](), [pypi](), [release](), [release-notes](), [tensorflow](), [tensorflow-core](), [tensorflowlite]() ### AI overview TensorFlow 2.19 introduces C++ API changes in LiteRT, adds bfloat16 support for the tflite casting operation, and deprecates tf.lite.Interpreter in favor of ai_edge_litert.interpreter. The release also stops publishing libtensorflow packages, although they remain extractable from the PyPI package. Updates for multi-backend Keras are directed to keras.io. ### Source excerpt Posted by the TensorFlow team TensorFlow 2.19 has been released! Highlights of this release include changes to the C++ API in LiteRT, bfloat16 support for tflite casting, discontinue of releasing libtensorflow packages. Learn more by reading the full release notes. Note: Release updates on the new multi-backend Keras will be published on keras.io, starting with Keras 3.0. For more information, please see https://keras.io/keras_3/. TensorFlow Core LiteRT The public constants tflite::Interpreter:kTensorsReservedCapacity and tflite::Interpreter:kTensorsCapacityHeadroom are now const references, rather than constexpr compile-time constants. (This is to enable better API compatibility for TFLite in Play services while preserving the implementation flexibility to change the values of these constants in the future.) TF-Lite tfl.Cast op is now supporting bfloat16 in the runtime kernel. tf.lite.Interpreter gives a deprecation warning redirecting to its new location at ai_edge_litert.interpreter, as the API tf.lite.Interpreter will be deleted in TF 2.20. See the migration guide for details. Libtensorflow We have stopped publishing libtensorflow packages but it can still be unpacked from the PyPI package. ## "Llama 3.2 in Keras" DevFeed: ["Llama 3.2 in Keras"]() Original publisher: [Read original article]() Author: Martin Görner Published: 2024-10-21T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Keras](), [llama3](), [Large Language Model](), [tokenization](), [Fine-tuning](), [PyTorch](), [Tensorflow](), [Transformers]() Tags: [fine-tuning](), [keras](), [llama3](), [llm](), [llms](), [open-source](), [pytorch](), [tensorflow](), [tokenization](), [training](), [transformers]() ### AI overview The article introduces Llama 3.2 support in Keras, explaining that Hugging Face checkpoints can be loaded directly and converted on the fly when needed. It also describes Keras and keras-hub support for multiple backends, pretrained models, tokenization, preprocessing, training, and fine-tuning. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Announcing New Hugging Face and KerasHub integration DevFeed: [Announcing New Hugging Face and KerasHub integration]() Original publisher: [Read original article]() Author: Aritra Roy Gosthipaty Published: 2024-07-10T00:00:00Z Content type: news Language: en Sources: [Hugging Face - Blog]() Topics: [hugging face](), [Keras](), [Transformers](), [gemma](), [llama](), [Open Source]() Tags: [gemma](), [hugging-face](), [json](), [keras](), [llama](), [nlp](), [open-source](), [open-source-collab](), [pytorch](), [tensorflow](), [transformers]() ### AI overview The article announces an integration between Hugging Face Transformers and KerasHub through a shared model save format. It allows KerasHub users to load many Transformers checkpoints, initially including Gemma, Llama 3, and PaliGemma, and use them with TensorFlow, JAX, or PyTorch backends. The integration handles conversion of configuration variables, weight names, and tokenizer vocabularies internally. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## What's new in TensorFlow 2.16 DevFeed: [What's new in TensorFlow 2.16]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2024-03-13T20:11:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [TensorFlow Core](), [Keras](), [Compiler](), [LLVM](), [Windows](), [pip](), [Python](), [MSVC]() Tags: [announcement](), [compiler](), [estimator](), [keras](), [llvm](), [msvc](), [python](), [release](), [tensorflow-core](), [windows]() ### AI overview TensorFlow 2.16 introduces Clang as the default compiler for TensorFlow CPU wheels on Windows, makes Keras 3 the default Keras version, and adds Python 3.12 support. The release also removes the tf.estimator API and changes the recommended installation method for Apple Silicon. ### Source excerpt Posted by the TensorFlow team TensorFlow 2.16 has been released! Highlights of this release (and 2.15) include Clang as default compiler for building TensorFlow CPU wheels on Windows, Keras 3 as default version, support for Python 3.12, and much more! For the full release note, please click here. Note: Release updates on the new multi-backend Keras will be published on keras.io starting with Keras 3.0. For more information, please see https://keras.io/keras_3/. TensorFlow Core Clang 17 Clang is now the preferred compiler to build TensorFlow CPU wheels on the Windows Platform starting with this release. The currently supported version is LLVM/clang 17. The official Wheels-published on PyPI will be based on Clang; however, users retain the option to build wheels using the MSVC compiler following the steps mentioned, as has been the case before. Intel owned the implementation and delivery of this change within the 3P Official Build program. Keras 3 Keras 3 will be the default Keras version for TensorFlow 2.16 onwards. You may need to update your script to use Keras 3. Please refer to the new Keras documentation for Keras 3 (https://keras.io/keras_3). Keras 2 will continue to be released alongside TensorFlow as tf_keras. To continue using Keras 2 with TensorFlow 2.16+: Install tf-keras vía pip install tf-keras~=2.16 Switch tf.keras to use Keras 2 (tf-keras), by setting environment variable TF_USE_LEGACY_KERAS=1 directly or in your Python program by doing import os;os.environ["TF_USE_LEGACY_KERAS"]="1". Please note that this needs to be set before importing TensorFlow and will set it for all packages in your Python runtime program. Estimator API tf.estimator API is removed. If you need to use the estimator API, you need to use TF 2.15 or an earlier version. Apple Silicon If you previously installed TensorFlow using pip install tensorflow-macos, please update your installation method. Use pip install tensorflow from now on. tensorflow-macos package will no longer receive ## What's new in TensorFlow 2.13 and Keras 2.13? DevFeed: [What's new in TensorFlow 2.13 and Keras 2.13?]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-07-25T16:00:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [TensorFlow Core](), [Keras](), [TensorFlow Lite](), [datasets](), [API]() Tags: [apple](), [datasets](), [google](), [keras](), [mac](), [python](), [quantization](), [release](), [tensorflow](), [tensorflow-core](), [tensorflow-lite](), [usability]() ### AI overview TensorFlow 2.13 and Keras 2.13 introduce Apple Silicon wheels, make the Keras V3 format the default for .keras files, and add improvements to TensorFlow Lite, tf.data, dataset padding, and CPU BF16 execution. ### Source excerpt Posted by the TensorFlow and Keras Teams TensorFlow 2.13 and Keras 2.13 have been released! Highlights of this release include publishing Apple Silicon wheels, the new Keras V3 format being default for .keras extension files and many more! TensorFlow Core Apple Silicon wheels for TensorFlow TensorFlow 2.13 is the first version to provide Apple Silicon wheels, which means when you install TensorFlow on an Apple Silicon Mac, you will be able to use the latest version of TensorFlow. The nightly builds for Apple Silicon wheels were released in March 2023 and this new support will enable more fine-grained testing, thanks to technical collaboration between Apple, MacStadium, and Google. tf.lite The Python TensorFlow Lite Interpreter bindings now have an option to use experimental_disable_delegate_clustering flag to turn-off delegate clustering during delegate graph partitioning phase. You can set this flag in TensorFlow Lite interpreter Python API interpreter = new Interpreter(file_of_a_tensorflowlite_model, experimental_preserve_all_tensors=False) The flag is set to False by default. This is an advanced feature in experimental that is designed for people who insert explicit control dependencies via with tf.control_dependencies() or need to change graph execution order. Besides, there are several operator improvements in TensorFlow Lite in 2.13 add operation now supports broadcasting up to 6 dimensions. This will remove explicit broadcast ops from many models. The new implementation is also much faster than the current one which calculates the entire index for both inputs the the input instead of only calculating the part that changes. Improve the coverage for 16x8 quantization by enabling int16x8 ops for exp, mirror_pad, space_to_batch_nd, batch_to_space_nd Increase the coverage of integer data types enabled int16 for less, greater_than, equal, bitcast, bitwise_xor, right_shift, top_k, mul, and int16 indices for gather and gather_nd enabled int8 for floor_div and floor_m ## KotlinDL 0.3: поддержка ONNX, Object Detection API, 20+ новых моделей в ModelHub, и много новых слоев DevFeed: [KotlinDL 0.3: поддержка ONNX, Object Detection API, 20+ новых моделей в ModelHub, и много новых слоев]() Original publisher: [Read original article]() Author: zaleslaw (JetBrains) Published: 2021-10-04T13:56:53Z Content type: release Language: ru Sources: [JetBrains RU]() Topics: [onnx](), [object-detection](), [Maven](), [Maven Central](), [Artificial Intelligence](), [Keras](), [PyTorch]() Tags: [big-data](), [central](), [deep-learning](), [fine-tuning](), [image-recognition](), [keras](), [kotlin](), [machine-learning](), [maven-central](), [object-detection](), [onnx](), [onnx-runtime](), [pytorch](), [tensorflow]() ### AI overview This release article presents KotlinDL 0.3, adding ONNX model support through ONNX Runtime Java API, new ModelHub models, an experimental high-level image-recognition API, additional layers, and Maven Central availability. It also describes object-detection support and fine-tuning limitations for ONNX models. ### Source excerpt Представляем версию 0.3 библиотеки глубокого обучения KotlinDL! Вас ждет множество новых фич: новые модели в ModelHub (включая модели для обнаружения объектов и распознавания лиц), возможность дообучать модели распознавания изображений, экспортированные из Keras и PyTorch в ONNX, экспериментальный высокоуровневый API для распознавания изображений и множество новых слоев, добавленных контрибьюторами. Также KotlinDL теперь доступен в Maven Central. В этой статье мы коснемся самых главных изменений релиза 0.3. Полный список изменений доступен по ссылке. Узнать больше о релизе ## KotlinDL 0.2: Functional API, зоопарк моделей c ResNet и MobileNet, DSL для обработки изображений DevFeed: [KotlinDL 0.2: Functional API, зоопарк моделей c ResNet и MobileNet, DSL для обработки изображений]() Original publisher: [Read original article]() Author: zaleslaw (JetBrains) Published: 2021-05-25T08:54:42Z Content type: release Language: ru Sources: [JetBrains RU]() Topics: [Kotlin](), [Deep neural networks](), [Maven Central](), [Tensorflow](), [Keras](), [ImageNet]() Tags: [dataset](), [deep-learning](), [image-processing](), [keras](), [kotlin](), [machine-learning](), [maven-central](), [neural-networks](), [tag-00486ebd8d87](), [tag-9d8cf70dc46c](), [tensorflow]() ### AI overview This article presents KotlinDL 0.2, a deep-learning library written in Kotlin with TensorFlow used for low-level computations. The release adds a Functional API for graph-based neural networks, an image-preprocessing DSL, new dataset types, and a model zoo containing ResNet, MobileNet, and VGG models. KotlinDL 0.2 is available on Maven Central. ### Source excerpt Представляем вам версию 0.2 библиотеки KotlinDL. Это библиотека глубокого обучения, где для низкоуровневых вычислений используется TensorFlow, но с высокоуровневым API и логикой, написанными на Kotlin. KotlinDL 0.2 теперь доступен на Maven Central (до этого он лежал на bintray, но закатилось солнышко земли опенсорсной). Появилось столько всего нового: новые слои, специальный DSL для препроцессинга изображений, новые типы датасетов, зоопарк моделей с несколькими моделями из семейства ResNet, MobileNet и старой доброй моделью VGG (рабочая лошадка, впрочем). В этой статье мы коснемся самых главных изменений релиза 0.2. Полный список изменений доступен по ссылке. Читать далее ## Neural network inference pipeline for videos in Tensorflow DevFeed: [Neural network inference pipeline for videos in Tensorflow]() Original publisher: [Read original article]() Author: Suresh Alse (noreply@blogger.com) Published: 2019-08-08T18:03:00Z Content type: tutorial Language: en Sources: [Life Plus Linux]() Topics: [Tensorflow](), [Inference](), [Machine learning](), [GPU](), [cpu](), [dataset](), [Keras]() Tags: [cpu](), [dataset](), [deeplearning](), [gpu](), [inference](), [keras](), [performance](), [pipeline](), [tensorflow]() ### AI overview A tutorial on building an efficient TensorFlow pipeline for video inference. It describes processing video frames in batches with tf.data.Dataset, parallelizing CPU preprocessing and I/O, and prefetching to keep CPU and GPU work supplied. ### Source excerpt Just as we saw a huge influx of images in the past decade or so, we are now seeing a lot of videos being produced on social media. The need to understand and moderate videos using machine learning has never been greater. In this post, I will show you how to build an efficient pipeline to processes videos in Tensorflow. For simplicity, let us consider a Resnet50 model pre-trained on Imagenet. Pretty straightforward, using tf.keras.applications Now, let us break it up to see what exactly is happening: We are loading the model with weights. We are reading an image and resizing it to 224x224. Do some preprocessing of the image. Run inference. Do some post processing. If we want to do something similar for large videos, we need to have a pipeline that takes a stream of frames from the video, applies preprocess transformations, run inference of frames, unravel the inferences and apply post processing. We can see that doing all these in a sequence - frame by frame is clearly not the right thing as it is slow and inefficient. In order to tackle this, we will use tf.data.Dataset and run inference in batch. First, lets create a generator that can produce frames from a video: We will use the tf.data.Dataset.from_generator method to create a dataset object out of this. Now let us define a function which does resizing, normalization and other preprocessing steps that are required on a batch of frames. Then, using the batch operation on the dataset created above, create a batch of size 64. Map the preprocess method that we defined onto the batch in parallel on CPU as it is a CPU intensive task. It is important to make sure that I/O is parallelized as much as possible. For best performance, instructions that are well suited for CPU should run on CPU and the ones suited for GPU should run on GPU. Also, If you observe the code above, we are prefetching. What this means is that, before consuming the dataset, a batch of 64 frames are preprocessed and is ready for consumption. By the t ## ThisEmoteDoesNotExist: Training a GAN for Twitch Emotes DevFeed: [ThisEmoteDoesNotExist: Training a GAN for Twitch Emotes]() Original publisher: [Read original article]() Author: Avery Gnolek Published: 2019-07-24T22:05:46Z Content type: tutorial Language: en Sources: [Twitch]() Topics: [Twitch](), [Deep learning](), [Keras](), [datasets](), [Python](), [pixel]() Tags: [dataset](), [deep-learning](), [engineering](), [keras](), [machine-learning](), [neural-networks](), [python](), [training](), [twitch]() ### AI overview A developer describes building a progressive-growing GAN for Twitch emotes as a personal machine-learning project. The article covers scraping roughly 2 million Twitch emote assets, implementing a proof-of-concept GAN with Keras, and training it on a random 200,000-image sample. ### Source excerpt The idea for this project began when a coworker and I were talking about NVIDIA's photo-realistic generated human faces using StyleGAN and they mentioned "I wish someone made one of those for Twitch emotes." I had always wanted to take some time to learn more about convolution neural networks and was in the middle of a machine learning project for work, so it seemed like trying to build this would be a quick and relevant personal project. The original plan (with my time estimates): Scrape all of the Twitch emote image assets (1 day) Write a progressive growing GAN implementation using Keras as a proof of concept (1 week) Adapt the emote dataset for use with a real research-caliber GAN implementation (1-2 days) Train the GAN on the emote dataset (1 day) 1 . Scrape all of the emote image assets This part of the project was actually quite straightforward. Twitch stores all of the emote images on a CDN using a monotonically increasing numeric emote_id. Each emote is available in three different sizes (1.0, 2.0, 3.0) corresponding to the resolutions of 28x28, 56x56, and 112x112. emoticons/778927/1.0emoticons/778927/2.0emoticons/v1/778927/3.0 I wrote a quick python scraper which would go through ~2 million emote_ids of three different sizes and download the images locally. Even at a modest 200 requests per second, this was able to finish overnight. In fact, I think the limiting factor for the speed of this step was actually writing the image files to my HDD, not the network requests themselves. So far, I was right on track with my time estimate. 2. Write a progressive growing GAN implementation using Keras as a proof of concept As I had no experience with CNNs or deep learning before this project, I wanted to at least attempt to write a progressive growing GAN myself as a way to learn before switching to an existing implementation. As Twitch emotes are not even power of two sizes, it was not possible to exactly replicate the 4x4 pixel to 128x128 pixel growing architecture ## Presenting Project Ergo: How to Build an Airplane Detector for Satellite Imagery With Deep Learning DevFeed: [Presenting Project Ergo: How to Build an Airplane Detector for Satellite Imagery With Deep Learning]() Original publisher: [Read original article]() Author: Simone Margaritelli Published: 2018-11-22T17:15:50Z Content type: tutorial Language: en Sources: [evilsocket]() Topics: [Keras](), [Tensorflow](), [Framework](), [Deep learning](), [Deep neural networks](), [datasets](), [Open Source](), [Code](), [Development](), [Back end](), [Python](), [Shell]() Tags: [cnn](), [code](), [computer-vision](), [convolutional-neural-networks](), [cpu](), [cuda](), [cudnn](), [cybersecurity](), [deep-learning](), [deep-neural-networks](), [dnn](), [ergo](), [how-to](), [image-classification](), [keras](), [machine-learning](), [neural-networks](), [nvidia](), [open-source](), [planes](), [planes-detector](), [planesnet](), [project-release](), [python](), [shell](), [tensorflow](), [tf](), [train](), [training](), [tutorial]() ### AI overview The article introduces Project Ergo, an open-source framework and manager for Keras-based machine-learning projects. It demonstrates prototyping, training, and testing a convolutional neural network with the PlanesNet dataset to build an airplane detector for satellite imagery, including CPU and GPU setup considerations. ### Source excerpt It's been a while that i've been quite intensively playing with Deep Learning both for work related research and personal projects. More specifically, I've been using the Keras framework on top of a TensorFlow backend for all sorts of stuff. From big and complex projects for malware detection, to smaller and simpler experiments about ideas i just wanted to quickly implement and test - it didn't really matter the scope of the project, I always found myself struggling with the same issues: code reuse over tens of crap python and shell scripts, datasets and models that are spread all over my dev and prod servers, no real standard for versioning them, no order, no structure. So a few days ago I started writing what it was initially meant to be just a simple wrapper for the main commands of my training pipelines but quickly became a full-fledged framework and manager for all my Keras based projects. Today I'm pleased to open source and present project Ergo by showcasing an example use-case: we'll prototype, train and test a Convolutional Neural Network on top of the PlanesNet raw dataset in order to build an airplane detector for satellite imagery. ## Deep NLP-based Recommenders at Finn.no DevFeed: [Deep NLP-based Recommenders at Finn.no]() Original publisher: [Read original article]() Author: Simen Eide Published: 2017-09-08T13:56:49Z Content type: tutorial Language: en Sources: [Finn.no]() Topics: [Natural language processing](), [Deep learning](), [Embeddings](), [recommendations](), [Keras](), [Hackathon]() Tags: [data](), [deep-learning](), [embeddings](), [hackathon](), [keras](), [model-architecture](), [neural-networks](), [nlp](), [recommendations]() ### AI overview The article describes a FINN.no hackathon project exploring deep NLP-based recommendations for classified ads. The team used categorized ad data, word embeddings, and a convolutional neural network architecture to model similarity, but the supplied text does not include the final performance results. ### Source excerpt During a hackathon at FINN.no, we figured we wanted to learn more about deep NLP-models. FINN.no has a large database with ads of people trying to sell stuff (around 1 million active ads at any time), and they are categorized into a category tree with three or four layers. For example, full suspension bikes can be found under "Sport and outdoor activities" / "Bike sport" / "Full suspension bikes". In our daily jobs we are working on recommendations. There, we already have a content based (tf-idf) recommender build on Solr's More Like This. It seems to work well in areas where our collaborative filtering approaches does not. Would it be possible to build a deep learning NLP-model of similar performance? To achieve a measure of similarity, building a classifier of the previously mentioned categories seemed like a good choice, since we already had a lot of pre-existing data. The NLP team at Schibsted had already tokenized around six million ads as well as trained a word2vec model for us - we were ready to roll! Some preprocessing still had to be done. We ran through all ads, concatenated the title and description strings, and after a quick look at the data took the first 15 words of each ad. Model architecture proposed by the paper Our initial experiments were done with a simple "Bag of words" model included in the Keras repository, but we promptly switched over to "Convolutional Neural Networks for Sentence Classification" based architecture after hearing about it from our colleague, Tobias. By looking at the first 15 words of the ad, and using 200 dimensional embeddings for each word, our input is transformed into a 15x200 matrix. We apply three different convolutions on each document. The three convolutions looks at 2, 3 and 4 words (kernel sizes) in each convolution. It then max-pools each over the whole document, so that you end up with one value per document per convolution. For each kernel size you do 100 different filters. Finally you add a dense layer for clas