IBM Journey to AI blog

OCTOBER 12, 2023

These models rely on learning algorithms that are developed and maintained by data scientists. In other words, traditional machine learning models need human intervention to process new information and perform any new task that falls outside their initial training. For example, Apple made Siri a feature of its iOS in 2011.

Artificial Intelligence 96

Artificial Intelligence Artificial Intelligence Machine Learning Machine Learning 96

Heartbeat

OCTOBER 9, 2023

These ground-breaking areas redefine how we connect with and learn from our collective past. Computer vision algorithms can reconstruct a highly detailed 3D model by photographing objects from different perspectives. But computer vision algorithms can assist us in digitally scanning and preserving these priceless manuscripts.

Algorithm 52

Algorithm Deep Learning Deep Learning Machine Learning 52

AWS Machine Learning Blog

OCTOBER 10, 2023

Machine learning (ML), especially deep learning, requires a large amount of data for improving model performance. Federated learning (FL) is a distributed ML approach that trains ML models on distributed datasets. If you want to customize the aggregation algorithm, you need to modify the fedAvg() function and the output.

AWS 113

AWS ML ML Algorithm 113

AWS Machine Learning Blog

MAY 2, 2023

There are a few limitations of using off-the-shelf pre-trained LLMs: They’re usually trained offline, making the model agnostic to the latest information (for example, a chatbot trained from 2011–2018 has no information about COVID-19). If you have a large dataset, the SageMaker KNN algorithm may provide you with an effective semantic search.

Algorithm 84

Algorithm Machine Learning Machine Learning Natural Language Processing 84

Hacker News

MARCH 25, 2022

“Transformers made self-supervised learning possible, and AI jumped to warp speed,” said NVIDIA founder and CEO Jensen Huang in his keynote address this week at GTC. Transformers are in many cases replacing convolutional and recurrent neural networks (CNNs and RNNs), the most popular types of deep learning models just five years ago.

Machine Learning 182

Machine Learning Machine Learning AI AI 182

Mlearning.ai

JULY 30, 2023

What we are looking for in these algorithms is to output a list of features along with corresponding importance values. With most ML use cases moving to deep learning, models’ opacity has increased significantly. Most feature-importance algorithms deal very well with dense and categorical features.

Python 52

Python Machine Learning Machine Learning Algorithm 52

IBM Data Science in Practice

JULY 5, 2023

In Otter-Knoweldge, we use different pre-trained models and/or algorithms to handle the different modalities of the KG, what we call handlers. These handlers might be complex pre-trained deep learning models, like MolFormer or ESM, or simple algorithms like the morgan fingerprint. Overington. ISSN 0305–1048. Huang, K. &

Database 130

Database Python Algorithm Deep Learning 130

AWS Machine Learning Blog

APRIL 6, 2023

We also demonstrate the performance of our state-of-the-art point cloud-based product lifecycle prediction algorithm. For example, in the 2019 WAPE value, we trained our model using sales data between 2011–2018 and predicted sales values for the next 12 months (2019 sale). We next calculated the MAPE for the actual sales values.

Machine Learning 94

Machine Learning Machine Learning ML ML 94

DataRobot Blog

MAY 26, 2022

When the FRB’s guidance was first introduced in 2011, modelers often employed traditional regression -based models for their business needs. While SR 11-7 is prescriptive in its guidance, one challenge that validators face today is adapting the guidelines to modern ML methods that have proliferated in the past few years.

ML 52

ML ML Machine Learning Machine Learning 52

AWS Machine Learning Blog

APRIL 19, 2023

We use Amazon SageMaker to train a model using the built-in XGBoost algorithm on aggregated features created from historical transactions. It’s easy to learn Flink if you have ever worked with a database or SQL-like system by remaining ANSI-SQL 2011 compliant.

ML 84

ML ML Apache Kafka SQL 84

Explosion

MARCH 17, 2019

It’s widely used in production and research systems for extracting information from text, developing smarter user-facing features, and preprocessing text for deep learning. In 2011, deep learning methods were proving successful for NLP, and techniques for pretraining word representations were already in use.

Python 52

Python Natural Language Processing Deep Learning Deep Learning 52

Hacker News

FEBRUARY 14, 2023

And in fact the big breakthrough in “deep learning” that occurred around 2011 was associated with the discovery that in some sense it can be easier to do (at least approximate) minimization when there are lots of weights involved than when there are fairly few. There’s the raw corpus of examples of language.

Machine Learning 182

Machine Learning Machine Learning Algorithm Artificial Intelligence 182

Mlearning.ai

JUNE 5, 2023

Many Libraries: Python has many libraries and frameworks (We will be looking some of them below) that provide ready-made solutions for common computer vision tasks, such as image processing, face detection, object recognition, and deep learning. It is a fork of the Python Imaging Library (PIL), which was discontinued in 2011.

Deep Learning 52

Deep Learning Deep Learning Python Machine Learning 52

ML Review

MAY 3, 2018

Much the same way we iterate, link and update concepts through whatever modality of input our brain takes — multi-modal approaches in deep learning are coming to the fore. While an oversimplification, the generalisability of current deep learning approaches is impressive.

Deep Learning 52

Deep Learning Deep Learning Natural Language Processing Machine Learning 52