Machine Learning

TensorFlow is one of the leading tools for training deep learning models. Outside that space, it may seem intimidating and unnecessary, but it has many creative uses—like producing highly effective adversarial input for black-box AI systems.

Pre-trained models are making waves in the deep learning world. Using massive pre-training datasets, these NLP models bring previously unheard-of feats of AI within the reach of app developers.

For those working with AI, the future is certainly exciting. At the same time, there is a general sense that AI suffers from one pesky flaw: AI in its current state can be unpredictably unreliable.

IMDb ratings have genre bias: For example, dramas tend to score higher. Removing common feature bias and keeping unique characteristics, it's possible to create a new, refined score based on IMDb information.

Supervised learning is the key to computer vision and deep learning. However, what happens when you don’t have access to large, human-labeled datasets? In this article, Toptal Computer Vision Developer Urwa Muaz demonstrates the potential of semi-supervised image classification using unlabeled datasets.

Unwanted AI bias is already a widespread problem. Machine learning models can replicate or exacerbate existing biases, often in ways that are not detected until release. So what can be done about it?

Data collection and preparation slow down traditional NLP projects. However, transfer learning and BERT can reduce the amount of data required and change the way companies execute NLP projects.

Natural language processing (NLP) has become one of the most researched subjects in the field of AI. This interest is driven by applications that have been brought to market in recent years. In this article, Toptal Deep Learning Developer Maximilian Hopf introduces you to Google Natural Language API and Google AutoML Natural Language.

The increasing accuracy of machine learning systems has resulted in a flood of applications using them. As machine learning models matured and improved, so did ways of attacking them. In this article, Toptal Python Developer Pau Labarta Bajo examines the world of adversarial machine learning, explains how ML models can be attacked, and what you can do to safeguard them against attack.