This blog post is part of a mini-series that talks about the different aspects of building a PyTorch Deep Learning project using Variational Autoencoders. In Part 1, we looked at the variational…
Blog post
:pencil2: Web-based image segmentation tool for object detection, localization, and keypoints - jsbroks/coco-annotator
Rice University computer scientists have demonstrated artificial intelligence (AI) software that runs on commodity processors and trains deep neural networks 15 times faster than platforms based on graphics ...
See how to build end-to-end NLP pipelines in a fast and scalable way on GPUs — from feature engineering to inference.
Keep your neural network alive by understanding the downsides of ReLU
Reinforcement learning (RL) is a powerful type of AI technology that can learn strategies to optimally control large, complex systems.
Algorithms off the convex path.
In recent years, GANs (generative adversarial networks) have been all the rage in the field of deep-learning generative models, leaving…
The dogfighting AI DARPA is developing is set to make the challenging migration from a synthetic environment to the real world soon.
Computer scientists from the University at Buffalo used the method to successfully detect Deepfakes taken from This Person Does Not Exist.
340 votes, 28 comments. If anyone wants to brush up on recent methods in EBMs, Normalizing Flows, GANs, VAEs, and Autoregressive models, I just…
Deep Nostalgia AI brings your photos to life just like in the Harry Potter movies.
Building an app for blood cell count detection.
The NLP application ecosystem is in its earliest stages, and it's not yet clear whether GPT-3 or a different model will be the foundation.
:extract_focal()/https%3A%2F%2Fpocket-syndicated-images.s3.amazonaws.com%2Farticles%2F5812%2F1601307462_Lung-Scan_2880x1860_Lede.jpg)
The laws of physics stay the same no matter one’s perspective. Now this idea is allowing computers to detect features in curved and higher-dimensional space.
The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design. Equivariant networks have shown excellent performance and...
Synthetic data can be used to test new products and services, validate models, or test performances because it mimics the statistical property of production data. Today you'll find different types of structured and unstructured synthetic data.
Introduction
The error backpropagation learning algorithm is a supervised learning technique for neural networks that calculates the gradient of descent for weighting different variables.
A simple technique for boosting accuracy on ANY model you use
The data science and artificial intelligence terms you need while reading the latest research
Speech and natural language processing (NLP) have become the foundation for most of the AI development in the enterprise today, as textual data represents a significant portion of unstructured content.
Activation functions are functions which take an input signal and convert it to an output signal. Activation functions introduce…
The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been...
Browse 31 tasks • 61 datasets • 57
Recently, a colleague of mine asked me a few questions like “why do we have so many activation functions?”, “why is that one works better…
Activation functions are functions that we apply in neural networks after (typically) applying an affine transformation combining weights and input features. They are typically non-linear functions. The rectified linear unit, or ReLU, has been the most popular in the past…
Reverse engineering the curve detection algorithm from InceptionV1 and reimplementing it from scratch.
We present Text2Gestures, a transformer-based learning method to interactively generate emotive full-body gestures for virtual agents aligned with natural language text inputs. Our method generates…
The memory capacity of embedding tables in deep learning recommendation models (DLRMs) is increasing dramatically from tens of GBs to TBs across the industry. Given the fast growth in DLRMs, novel...
Browse 1109 deep learning methods for General.
Classifying cross-topic natural language texts based on their argumentative structure using deep learning
The concept: When we look at a chair, regardless of its shape and color, we know that we can sit on it. When a fish is in water, regardless of its location, it knows that it can swim. This is known as the theory of affordance, a term coined by psychologist James J. Gibson. It…
A Gentle Guide to the REINFORCE algorithm, in Plain English
Why is Model Compression important? A significant problem in the arms race to produce more accurate models is complexity, which leads to…
None
Papers with Code indexes various machine learning artifacts — papers, code, results — to facilitate discovery and comparison. Using this…
If you have ever had to tinker with anchor boxes, you were probably frustrated, confused and saying to yourself, “There must be another…
A recent article came out comparing public cloud providers’ face detection APIs. I was very surprised to see all of the detectors fail to…
**Pose Estimation** is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation. A common…
Dimensionality reduction is the task of reducing the dimensionality of a dataset. ( Image credit: [openTSNE](https://github.com/pavlin-policar/openTSNE) )
Bayesian Inference is a methodology that employs Bayes Rule to estimate parameters (and their full posterior).
**Transfer Learning** is a machine learning technique where a model trained on one task is re-purposed and fine-tuned for a related, but different task. The idea behind transfer learning is to leverage the knowledge learned from a pre-trained model to solve a new, but related…
**Representation Learning** is a process in machine learning where algorithms extract meaningful patterns from raw data to create representations that are easier to understand and process. These representations can be designed for interpretability, reveal hidden features, or be…
**Object tracking** is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment. State-of-the-art methods involve…
**Image Retrieval** is a fundamental and long-standing computer vision task that involves finding images similar to a provided query from a large database. It's often considered as a form of fine-grained, instance-level classification. Not just integral to image recognition…
**Zero-shot learning (ZSL)** is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning. Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the…