Goto

Collaborating Authors

Perceptrons


Perceptron: Let's break down thinking into calculations

#artificialintelligence

Perceptron is the most fundamental model of how the brain thinks. Fundamental in the sense that it is the most minimum function that is at least required to perform brain like thinking. Thinking can also be thought of as a calculation and calculation is best described in terms of functions. I described perceptron as the most fundamental model which also means it is the most minimum form of function that is at least required for brain-like thinking to perform. If we go even below this the full functionality of the brain will not be possible.


Transformers in Video Understanding

#artificialintelligence

Videos are everywhere and they are only increasing over time. One way to solve problems related to videos is by using individual frames for classification. For working on space and time, machine learning researchers have proposed many solutions and one of the recent techniques is using transformers. Transformers were introduced in Natural Language Processing. Now transformers are almost everywhere.


Statistical learning theory and empirical risk

#artificialintelligence

Here, I'll be giving an overview and theoretical concepts of the statistical learning. Supervised learning can play a key role in learning from examples. From this algorithm, useful information can be easily extracted from large datasets, the problem of learning from examples consecutively involves approximating functions from a sparse and noisy data. In supervised learning, network is trained on a dataset of the form, T {xk, dk} from k 1 to Q. It is observed that using MLP multilayer perceptron with sufficient number of hidden neurons, it is possible to approximate a given function to any arbitrary degree of accuracy.


Weight Decay in Multilayer Perceptrons in Deep Learning Computation

#artificialintelligence

Weight decay, also known as L2 regularization, is a technique used in machine learning to prevent overfitting by adding a penalty term to the objective function that is being optimized. The goal of weight decay is to reduce the complexity of the model by limiting the size of the weights, which can help to prevent overfitting and improve the generalization ability of the model. Weight decay is typically implemented by adding a term to the objective function that is proportional to the sum of the squares of the weights. The strength of the weight decay penalty is controlled by a hyperparameter called the decay rate or regularization strength, which determines the amount of weight decay applied to the model. For example, let's say we are training a linear regression model to predict the price of a house based on the number of bedrooms and the square footage.


Council Post: AutoML's Rise To Prominence

#artificialintelligence

The concept of machine learning first came up when Alan Turing wrote a paper about whether machines could achieve artificial intelligence. In 1957, Frank Rosenblatt designed the first neural network, called the perceptron algorithm. They are called neural networks because they are thought to be designed based on a simplistic way of how the brain works in order to process information. Though there were some initial real-world applications for machine learning, such as the Madaline network, which could eliminate phone lines' background echo, it wouldn't rise back to prominence until computer vision applications emerged in 2012. In 2012, AlexNet, a deep neural network designed by Alex Krizhevsky achieved 84% accuracy in Imagenet's image classification contest.


Image Deblurring using MAXIM. Using the pre-trained MAXIM model to…

#artificialintelligence

There are new initiatives undertaken on Transformers and Multi-layer perceptron (MLP) models that provide new network architectural designs for computer vision tasks. Although these models proved to be effective in many vision tasks such as image recognition, there remain challenges in adapting them for low-level vision. The inflexibility to support high-resolution images and the limitations of local attention are perhaps the main bottlenecks. MAXIM is a multi-axis MLP-based architecture that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks. MAXIM uses a UNet-shaped hierarchical structure and supports long-range interactions enabled by spatially-gated MLPs. Specifically, MAXIM contains two MLP-based building blocks: a multi-axis gated MLP that allows for efficient and scalable spatial mixing of local and global visual cues, and a cross-gating block, an alternative to cross-attention, which accounts for cross-feature conditioning. Both these modules are exclusively based on MLPs, but also benefit from being both global and'fully convolutional', two properties that are desirable for image processing. The proposed MAXIM model achieves state-of-the-art performance on more than ten benchmarks across a range of image processing tasks, including denoising, deblurring, deraining, dehazing, and enhancement while requiring fewer or comparable numbers of parameters and FLOPs than competitive models.


Sketch Guidance

#artificialintelligence

Text-to-Image models have introduced a remarkable leap in the evolution of machine learning, demonstrating high-quality synthesis of images from a given text-prompt. However, these powerful pretrained models still lack control handles that can guide spatial properties of the synthesized images. In this work, we introduce a universal approach to guide a pretrained text-to-image diffusion model, with a spatial map from another domain (e.g., sketch) during inference time. Unlike previous works, our method does not require to train a dedicated model or a specialized encoder for the task. Our key idea is to train a Latent Guidance Predictor (LGP) - a small, per-pixel, Multi-Layer Perceptron (MLP) that maps latent features of noisy images to spatial maps, where the deep features are extracted from the core Denoising Diffusion Probabilistic Model (DDPM) network.


Machine learning and statistic analysis to predict drug treatment outcome in pediatric epilepsy patients with tuberous sclerosis complex - ScienceDirect

#artificialintelligence

We aimed to investigate the association between multi-modality features and epilepsy drug treatment outcomes and propose a machine learning model to predict epilepsy drug treatment outcomes with multi-modality features. This retrospective study consecutively enrolled 103 epilepsy children with rare TSC. Multi-modality data were used to characterize risk factors for epilepsy drug treatment outcome of TSC, including clinical data, TSC1, and TSC2 genes test results, magnetic resonance imaging (MRI), computerized tomography (CT), and electroencephalogram (EEG). Three common feature selection methods and six common machine learning models were used to find the best combination of feature selection and machine learning model for epilepsy drug treatment outcomes prediction with multi-modality features for TSC clinical application. The analysis of variance based on selected 35 features combined with multilayer perceptron (MLP) model achieved the best area-under-curve score (AUC) of 0.812 (±0.005).


Perceptron: AI that sees with sound, learns to walk and predicts seismic physics

#artificialintelligence

Research in the field of machine learning and AI, now a key technology in practically every industry and company, is far too voluminous for anyone to read it all. This column, Perceptron, aims to collect some of the most relevant recent discoveries and papers -- particularly in, but not limited to, artificial intelligence -- and explain why they matter. This month, engineers at Meta detailed two recent innovations from the depths of the company's research labs: an AI system that compresses audio files and an algorithm that can accelerate protein-folding AI performance by 60x. Elsewhere, scientists at MIT revealed that they're using spatial acoustic information to help machines better envision their environments, simulating how a listener would hear a sound from any point in a room. Meta's compression work doesn't exactly reach unexplored territory. Last year, Google announced Lyra, a neural audio codec trained to compress low-bitrate speech.


Neural Networks

#artificialintelligence

Picture this: A newborn baby gets thrown into a deep-end pool and needs to learn how to swim for survival. This newborn baby will go through the method of trial and error to improve itself. It will learn from its mistakes and improve its accuracy over time. An artificial neural network (ANN) is a computing system that can learn on its own. It creates an adaptive system that computers use to learn from their mistakes and improve continuously.