Neural Networks | Нейронные сети
11.6K subscribers
801 photos
182 videos
170 files
9.45K links
Все о машинном обучении

По всем вопросам - @notxxx1

№ 4959169263
Download Telegram
🎥 101. Чем может и чем не может наука о данных помочь науке о литературе — Борис Орехов
👁 1 раз 1661 сек.
В рамках мероприятия "Data & Science: цифровые методы в гуманитарных науках" Борис Орехов рассказал, что наука о данных и литературоведение гораздо больше похожи, чем кажется на первый взгляд.

Обе отрасли знания пытаются найти неочевидные закономерности в сложно организованных объектах. Но не любой привычный исследователю данных подход будет осмыслен в исследовании литературы. Борис на примерах показывает, какие методы работают и приносят пользу, а какие пока остаются игрушками — и почему.

Другие доклады
​Tinkering with Tensors and Other Great Adventures
A meditation on implementing your first deep learning paper, while (loosely) maintaining your sanity.
https://towardsdatascience.com/tinkering-with-tensors-and-other-great-adventures-260572a403e8

🔗 Tinkering with Tensors and Other Great Adventures
A meditation on implementing your first deep learning paper, while (loosely) maintaining your sanity.
​Simulated Policy Learning in Video Models

http://ai.googleblog.com/2019/03/simulated-policy-learning-in-video.html

🔗 Simulated Policy Learning in Video Models
Posted by Łukasz Kaiser and Dumitru Erhan, Research Scientists, Google AI Deep reinforcement learning (RL) techniques can be used to le...
Российский Завод Колесных Проставок ZUZ
Шайбы сквозные
Расширители колеи
Переходники для дисков

Самые низкие цены на рынке 📉
Высокопрочный алюминий 👊🏻
Комплекты в наличии
Заказ от 1 штуки

Изготовление по вашим параметрам 🔧
автомобили
квадроциклы
прицепы

Проконсультироваться и заказать:
По телефону/Viber/Whatsapp +7 (982) 277 44 44
В группе: vk.com/zavodprostavok
На официальном сайте компании: http://zlatural74.ru/

Всех участников в сфере авто - мото бизнеса приглашаем к сотрудничеству 🤝

----------------------------------------------------------------------------
Проставки на автомобили: Уаз (Uaz), Нива (Niva), Ваз, Лада (Lada), Тойота (Toyota), Бмв (Bmw), Мерседес (Mercedes), Ауди (Audi),Фольксваген (Volkswagen),Ситроен (Citroen),Форд (Ford), Киа (Kia), Хендай (Hyundai), Лексус (Lexus), Мазда (Mazda), Митсубиси (Mitsubishi), Ниссан (Nissan), Опель (Opel), Пежо (Peugeot), Субару (Subaru), Cузуки (Suzuki), Вольво (Volvo), Санг Йонг (Ssangyong), Шевроле (Chevrolet)...
Проставки на квадроциклы: Поларис (Polaris), Brp, Can-Am, Yamaha (Ямаха), ArcticCat (Арктик Кэт), Honda (Хонда), Kawasaki ( Кавасаки), Cfmoto (Си Эф Мото), Stels (Стелс), Suzuki (Сузуки), Рм (Русская Механика)...
Проставки на прицепы: МЗСА, ВЕКТОР, Трейлер, СаранскСпецТехника, Курганские прицепы, Кремень31, LAKER, PRESTIGE...

🔗
​Выкупят/не выкупят: наш ML-пилот в «Утконосе»

В этом посте речь пойдет про пилотное ML-исследование для гипермаркета «Утконос», где мы прогнозировали выкуп скоропортящихся товаров. При этом мы учли данные не только по остаткам на складе, но и производственный календарь с выходными и праздниками и даже погоду (жара, снег, дождь и град нипочем только «Taft’у Три погоды», но не покупателям). Теперь мы знаем, например, что «загадочная русская душа» особенно жаждет мяса по субботам, а белые яйца ценит выше коричневых. Но обо всем по порядку.https://habr.com/ru/company/jetinfosystems/blog/445190/

🔗 Выкупят/не выкупят: наш ML-пилот в «Утконосе»
В этом посте речь пойдет про пилотное ML-исследование для гипермаркета «Утконос», где мы прогнозировали выкуп скоропортящихся товаров. При этом мы учли данные не...
​Quantum Machine Learning - Prof. Lilienfeld

🔗 Quantum Machine Learning - Prof. Lilienfeld
Prof. O. Anatole von Lilienfeld of the University of Bassel presented his labs work on Quantum Machine Learning at the 2017 Conference on Neural Information ...
https://arxiv.org/abs/1903.08114

🔗 Exact Gaussian Processes on a Million Data Points
Gaussian processes (GPs) are flexible models with state-of-the-art performance on many impactful applications. However, computational constraints with standard inference procedures have limited exact GPs to problems with fewer than about ten thousand training points, necessitating approximations for larger datasets. In this paper, we develop a scalable approach for exact GPs that leverages multi-GPU parallelization and methods like linear conjugate gradients, accessing the kernel matrix only through matrix multiplication. By partitioning and distributing kernel matrix multiplies, we demonstrate that an exact GP can be trained on over a million points in 3 days using 8 GPUs and can compute predictive means and variances in under a second using 1 GPU at test time. Moreover, we perform the first-ever comparison of exact GPs against state-of-the-art scalable approximations on large-scale regression datasets with $10^4-10^6$ data points, showing dramatic performance improvements.
​A quantum version of the building block behind neural networks could be exponentially more powerful. By Emerging Technology from the arXiv: https://www.technologyreview.com/…/machine-learning-meet-q…/

An Artificial Neuron Implemented on an Actual Quantum Processor, https://arxiv.org/abs/1811.02266

#artificialinteligence #quantumcomputing #neuralnetworks #machinelearning #processors

🔗 An Artificial Neuron Implemented on an Actual Quantum Processor
Artificial neural networks are the heart of machine learning algorithms and artificial intelligence protocols. Historically, the simplest implementation of an artificial neuron traces back to the classical Rosenblatt's `perceptron', but its long term practical applications may be hindered by the fast scaling up of computational complexity, especially relevant for the training of multilayered perceptron networks. Here we introduce a quantum information-based algorithm implementing the quantum computer version of a perceptron, which shows exponential advantage in encoding resources over alternative realizations. We experimentally test a few qubits version of this model on an actual small-scale quantum processor, which gives remarkably good answers against the expected results. We show that this quantum model of a perceptron can be used as an elementary nonlinear classifier of simple patterns, as a first step towards practical training of artificial quantum neural networks to be efficiently implemented o
🎥 Really Quick Questions - Nvidia Research
👁 21 раз 490 сек.
Nvidia is the inventor of the GPU! This tech company based in Silicon Valley has played a huge role in the deep learning revolution (which has relied primarily on GPUs for computing), and its transformed many industries. In this video, I interview Bryan Catanzaro, the Vice President of Applied Deep Learning Research at NVIDIA. Bryan got his PhD in AI from Berkeley, invented a language called Copperhead, and is an expert in parallel programming theory. Nvidia invited me to their annual conference, so I took
Курс «NLP with Deep Learning»

Наш телеграм канал - tglink.me/ai_machinelearning_big_data
1. Natural Language Processing with Deep Learning
2. Word Vector Representations: word2vec
3. GloVe: Global Vectors for Word Representation
4. Word Window Classification and Neural Networks
5. Backpropagation and Project Advice
6. Dependency Parsing
7. Introduction to TensorFlow
8. Recurrent Neural Networks and Language Models
9. Machine Translation and Advanced Recurrent LSTMs and GRUs

🎥 Lecture 1 | Natural Language Processing with Deep Learning
👁 877 раз 4301 сек.
Lecture 1 introduces the concept of Natural Language Processing (NLP) and the problems NLP faces today. The concept of representing words as numeri...

🎥 Lecture 2 | Word Vector Representations: word2vec
👁 115 раз 4697 сек.
Lecture 2 continues the discussion on the concept of representing words as numeric vectors and popular approaches to designing word vectors.

Key ...


🎥 Lecture 3 | GloVe: Global Vectors for Word Representation
👁 132 раз 4720 сек.
Lecture 3 introduces the GloVe model for training word vectors. Then it extends our discussion of word vectors (interchangeably called word embeddi...

🎥 Lecture 4: Word Window Classification and Neural Networks
👁 72 раз 4603 сек.
Lecture 4 introduces single and multilayer neural networks, and how they can be used for classification purposes.

Key phrases: Neural networks. Fo...


🎥 Lecture 5: Backpropagation and Project Advice
👁 31 раз 4700 сек.
Lecture 5 discusses how neural networks can be trained using a distributed gradient descent technique known as back propagation.

Key phrases: Neur...


🎥 Lecture 6: Dependency Parsing
👁 50 раз 4987 сек.
Lecture 6 covers dependency parsing which is the task of analyzing the syntactic dependency structure of a given input sentence S. The output of a ...

🎥 Lecture 7: Introduction to TensorFlow
👁 72 раз 4354 сек.
Lecture 7 covers Tensorflow. TensorFlow is an open source software library for numerical computation using data flow graphs. It was originally deve...

🎥 Lecture 8: Recurrent Neural Networks and Language Models
👁 36 раз 4683 сек.
Lecture 8 covers traditional language models, RNNs, and RNN language models. Also reviewed are important training problems and tricks, RNNs for oth...