All public logs

Combined display of all available logs of AI Wiki. You can narrow down the view by selecting a log type, the username (case-sensitive), or the affected page (also case-sensitive).

18:44, 2 March 2023 Elegant angel talk contribs created page Improving Language Understanding by Generative Pre-Training (Redirected page to Improving Language Understanding by Generative Pre-Training (GPT)) Tag: New redirect
18:21, 2 March 2023 Elegant angel talk contribs created page GPT-2 (Created page with "{{Needs Expansion}} GPT-2 is the 2nd GPT model released by OpenAI in February 2019. Although it is larger than its predecessor, GPT-1, it is very similar. The main difference is that GPT-2 can multitask. It is able to perform well on multiple tasks without being trained on any examples. GPT-2 demonstrated that language model could better comprehend natural language and perform better on more tasks when it is trained on a larger d...")
17:56, 2 March 2023 Elegant angel talk contribs created page GPT (Created page with "GPT-1 GPT-2 GPT-3 ChatGPT GPT-3.5")
17:55, 2 March 2023 Elegant angel talk contribs created page GPT-1 (Created page with "OpenAI released GPT-1 in June 2018. The developers found that combining the transformer architecture and unsupervised pertaining produced amazing results. GPT-1, according to the developers, was tailored for specific tasks in order to "strongly understand natural language." GPT-1 was an important stepping stone toward a language model that possesses general language-based abilitiess. It showed that language models can be efficiently pre-tra...")
16:56, 2 March 2023 Nicoboomer talk contribs created page Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers (VALL-E) (Created page with "{{see also|Papers}} ==Introduction== In the last decade, there have been significant advances in speech synthesis via neural networks and end to end modeling. Current text-to-speech (TTS), systems require high-quality data from recording studios. They also suffer from poor generalization for unseen speaker in zero-shot situations. A new TTS framework, VALL-E, has been developed to address this issue. It uses audio codec codes for an intermediate representation as well a...")
16:35, 2 March 2023 Nicoboomer talk contribs created page Template:Paper infobox (Created page with "<includeonly><div class="model"> <div class="heading">[[{{PAGENAME}}]]</div> <div style="width: 500px; display: flex; flex-direction: column;"> <div class="model-infobox-row"> {{#if:{{{name|}}}| <div class="model-infobox-cell">'''Name'''</div> <div class="model-infobox-cell">[[Has paper name::{{{name}}}]]</div> }} </div> <div class="model-infobox-row"> {{#if:{{{type|}}}| <div class="model-infobox-cell">'''Type'''</div> <div class="model-infobox-cell">{{#arraymap:{{{ty...")
16:19, 2 March 2023 User account Nicoboomer talk contribs was created
18:57, 1 March 2023 Alpha5 talk contribs created page Imbalanced dataset (Redirected page to Class-imbalanced dataset) Tag: New redirect
18:55, 28 February 2023 Alpha5 talk contribs created page Minority class (Created page with "{{see also|Machine learning terms}} ===Minority Class in Machine Learning== Minority class refers to a classification problem class with fewer instances or samples than its majority counterpart. For instance, in binary classification problems, if the positive class has more instances than the negative one, then it is considered the minority group. Multi-class problems also use this concept; minorities refer to classes with the fewest instances. Class imbalance is a prob...")
18:54, 28 February 2023 Alpha5 talk contribs created page Imbalanced data (Redirected page to Class-imbalanced dataset) Tag: New redirect
18:41, 28 February 2023 Alpha5 talk contribs created page Majority class (Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, the majority class is the more common label in a dataset that is imbalanced. For example, in a dataset where there are 80% "yes" and 20% "no", "yes" is the majority class. The opposite of the majority class the minority class. ==Impact on Model Performance== A majority class in a dataset can have an enormous effect on the performance of a machine le...")
18:29, 28 February 2023 Alpha5 talk contribs created page Mini-batch size (Redirected page to Batch size) Tag: New redirect
18:03, 28 February 2023 Alpha5 talk contribs created page Mini batch (Redirected page to Mini-batch) Tag: New redirect
18:03, 28 February 2023 Alpha5 talk contribs created page Minibatch (Redirected page to Mini-batch) Tag: New redirect
18:02, 28 February 2023 Alpha5 talk contribs created page Mini-batch (Created page with "{{see also|Machine learning terms}} ==Introduction== Mini-batch training is a machine learning technique used to efficiently train large datasets. This division of the entire dataset into smaller batches allows for faster training as well as improved convergence of the model to its optimal solution. ==Theoretical Background== Traditional machine learning relies on batch gradient descent to train the model on all data in one iteration. Unfortunately, when the dataset gro...")
16:58, 28 February 2023 Elegant angel talk contribs created page Data-centric AI (Redirected page to Data-centric AI (DCAI)) Tag: New redirect
16:57, 28 February 2023 Elegant angel talk contribs created page DCAI (Redirected page to Data-centric AI (DCAI)) Tag: New redirect
15:48, 28 February 2023 Elegant angel talk contribs created page Manipulation (Redirected page to Manipulation problem) Tag: New redirect
15:16, 28 February 2023 Elegant angel talk contribs created page Manipulation problem (Created page with "==Introduction== Artificial intelligence (AI) has revolutionized our lives, and we now use it for a wide range of applications, including image recognition, natural language processing, and machine learning. However, with every new technology comes a new set of challenges, and AI is no exception. One of the most significant challenges posed by AI is the "manipulation problem," which refers to the potential for AI systems to be used to target and manipulate individual use...")
12:34, 28 February 2023 Alpha5 talk contribs created page Layer (Created page with "{{see also|Machine learning terms}} ===Introduction to Layers in Machine Learning== Layers are a fundamental building block in artificial neural networks, machine learning algorithms modeled after the structure and function of the human brain. They perform computation on input data to produce outputs which can be used for making predictions or solving other problems. The number of layers within a neural network as well as its size and configuration determine its capacity...")
12:10, 28 February 2023 Alpha5 talk contribs created page Learning rate (Created page with "{{see also|Machine learning terms}} ==Introduction== In machine learning, learning rate is an influential hyperparameter that impacts how quickly a model learns and adapts to new data. It is used as a scalar value that adjusts model weights during training. In this article, we'll examine learning rate in detail: its definition, significance, and how it impacts performance of a machine learning model. ==Definition== Learning rate is a hyperparameter that controls the spe...")
11:42, 28 February 2023 Alpha5 talk contribs deleted page Data-centric AI (content was: "#REDIRECT Data-centric AI (DCAI)", and the only contributor was "Alpha5" (talk))
11:42, 28 February 2023 Alpha5 talk contribs deleted page DCAI (content was: "#REDIRECT Data-centric AI (DCAI)", and the only contributor was "Alpha5" (talk))
11:27, 28 February 2023 Elegant angel talk contribs created page Confident Learning (CL) (Created page with "==Introduction== Confident Learning (CL) is a subfield of supervised learning and weak-supervision aimed at characterizing label noise, finding label errors, learning with noisy labels and finding ontological issues. CL is based on the principles of pruning noisy data, counting to estimate noise and ranking examples to train with confidence. CL generalizes Angluin and Laird's classification noise process to directly estimate the joint distribution bet...")
11:04, 28 February 2023 Elegant angel talk contribs created page CL (Redirected page to Confident Learning (CL)) Tag: New redirect
11:03, 28 February 2023 Elegant angel talk contribs created page Confident learning (Redirected page to Confident learning (CL)) Tag: New redirect
08:53, 28 February 2023 Elegant angel talk contribs created page Data-centric AI (DCAI) (Created page with "==Introduction== Model-centric AI is the paradigm taught in most ML classes and revolves around producing the best model given a clean, well-curated dataset. In contrast, Data-centric AI involves systematically engineering data to build better AI systems. Data-centric AI can come in two forms: *algorithms that understand data and use that information to improve models *algorithms that modify data to improve ML models. Examples of this include curriculum learning (...")
08:53, 28 February 2023 User account Elegant angel talk contribs was created
08:52, 28 February 2023 User account ElegantA talk contribs was created
08:12, 28 February 2023 Alpha5 talk contribs created page DCAI (Redirected page to Data-centric AI (DCAI)) Tag: New redirect
08:12, 28 February 2023 Alpha5 talk contribs created page Data-centric AI (Redirected page to Data-centric AI (DCAI)) Tag: New redirect
19:03, 27 February 2023 Alpha5 talk contribs created page Automation bias (Created page with "{{see also|Machine learning terms}} ===Automation Bias in Machine Learning== Automated bias in machine learning refers to the phenomenon where a model inherits and amplifies any biases present in its training data, leading to biased or discriminatory outcomes. Machine learning algorithms are programmed with the purpose of learning patterns and relationships in training data and making predictions based on this learned information; however, if that data contains biased el...")
19:00, 27 February 2023 Alpha5 talk contribs created page Augmented reality (Created page with "{{see also|Machine learning terms}} ===Introduction to Augmented Reality in Machine Learning== Augmented Reality (AR) is the integration of digital information with the physical world, creating a hybrid environment that blends the real and virtual. Machine learning, on the other hand, is an area of artificial intelligence that develops algorithms and models to enable computers to learn from and make predictions based on data. When AR and machine learning come together, y...")
18:17, 27 February 2023 Alpha5 talk contribs created page Attribute (Created page with "{{see also|Machine learning terms}} ===Attribute in Machine Learning== An attribute, also referred to as a feature, is an identifiable property or characteristic of something being observed. In machine learning applications, attributes are employed to describe data instances or examples that feed into the model for training purposes. The objective is to extract meaningful and pertinent information from these attributes that can be used to make predictions about unseen da...")
18:09, 27 February 2023 Alpha5 talk contribs created page AUC (Area under the ROC curve) (Redirected page to AUC (Area Under the Curve)) Tag: New redirect
18:05, 27 February 2023 Alpha5 talk contribs created page Attribute sampling (Created page with "{{see also|Machine learning terms}} ===Attribute Sampling in Machine Learning== Attribute sampling is a technique in machine learning to randomly select some features from a dataset to train a model. This process can be done for various reasons, such as saving computational time during training, avoiding overfitting risks, and increasing model interpretability. In this article we'll examine different types of attribute sampling, their advantages and drawbacks, and when t...")
18:05, 27 February 2023 Alpha5 talk contribs created page Attention (Created page with "{{see also|Machine learning terms}} ==Introduction== Attention is a technique in machine learning that allows a model to focus on specific parts of an input while making predictions. Attention mechanisms enable models to selectively focus on certain parts of an input sequence - making them useful in tasks involving sequential or structured data. Attention models have become increasingly popular over the last few years, particularly in natural language processing (NLP). A...")
18:00, 27 February 2023 Alpha5 talk contribs created page Artificial general intelligence (Created page with "{{see also|Machine learning terms}} ===Introduction== Artificial General Intelligence (AGI) is a branch of artificial intelligence research that seeks to build machines capable of performing any intellectual task that a human can. This stands in stark contrast to narrow AI, which aims to do one specific thing like recognizing objects in an image or playing chess. AI research often strives to reach this ultimate goal, as it would require a machine with an understanding o...")
17:51, 27 February 2023 Alpha5 talk contribs created page Area under the ROC curve (Created page with "{{see also|Machine learning terms}} ==Introduction== The Receiver Operating Characteristic (ROC) curve is a widely-used visual representation of the performance of binary classifiers. It plots True Positive Rate (TPR) against False Positive Rate (FPR) over various threshold values for each classifier. The area under the ROC curve (AUC) serves as an aggregate metric that summarizes overall classifier performance across all possible threshold values. ==Methodology== Calcu...")
17:08, 27 February 2023 Alpha5 talk contribs created page Area under the PR curve (Created page with "{{see also|Machine learning terms}} ==Introduction== Evaluation of a model's performance in machine learning is essential to determine its capacity for accurately predicting output. One such performance indicator is the area under the Precision-Recall (PR) curve, which measures the tradeoff between precision and recall for different classification thresholds. Machine learning requires the evaluation of a classifier's performance as an essential step in the modeling proc...")
16:44, 27 February 2023 Alpha5 talk contribs created page AR (Created page with "{{see also|Machine learning terms}} ==Introduction== Machine learning is the study of teaching machines how to learn from data and make decisions based on that information. Recently, one area of machine learning that has seen great growth in popularity is augmented reality (AR). AR refers to the integration of computer-generated graphics or information into real life scenarios. ==Definition of Augmented Reality== Augmented reality (AR) is a technology that overlays digi...")
15:32, 27 February 2023 Alpha5 talk contribs created page Anomaly detection (Created page with "{{see also|Machine learning terms}} ==Introduction== Machine learning Anomaly detection is the process of recognizing data points that deviate from normal behavior in a dataset. These abnormal outcomes are known as anomalies, outliers, or exceptions. Anomaly detection plays an integral role in many domains such as fraud detection, network intrusion detection, and fault detection in industrial systems. ==Applications== Anomaly detection is used in many fields to detect a...")
15:32, 27 February 2023 Alpha5 talk contribs created page Agglomerative clustering (Created page with "{{see also|Machine learning terms}} ===Agglomerative Clustering in Machine Learning== Agglomerative Clustering is an unsupervised learning technique utilized in machine learning and data mining. This process groups objects together based on their similarity, with the primary goal of creating meaningful clusters. Each object in this agglomerative cluster starts as a singleton cluster and at each step the two closest clusters are merged until an ending criterion is met. =...")
15:15, 27 February 2023 Alpha5 talk contribs created page Agent (Created page with "{{see also|Machine learning terms}} ===Definition== Machine learning refers to an agent as a system or entity that can perceive its environment, make decisions, and take actions in order to reach certain goals or sets of goals. An agent is thus seen as autonomous decision-making entity operating within its environment that interacts with that environment in order to complete tasks. ==Types of Agents== Machine learning consists of two primary types of agents: reactive ag...")
14:58, 27 February 2023 Alpha5 talk contribs created page AdaGrad (Created page with "{{see also|Machine learning terms}} ===AdaGrad: An Optimization Algorithm for Stochastic Gradient Descent== AdaGrad is an effective optimization algorithm used in machine learning for training neural networks and other models that use stochastic gradient descent (SGD) to update their weights. John Duchi et al. first described AdaGrad in 2011 in their paper entitled "Adaptive Subgradient Methods for Online Learning and Stochastic Optimization." AdaGrad works by adapting...")
14:42, 27 February 2023 Alpha5 talk contribs created page Active learning (Created page with "{{see also|Machine learning terms}} ==Introduction== Active learning is a subfield of machine learning that seeks to enhance the performance of an algorithm by iteratively selecting informative samples from large pools of unlabeled data to be labeled by humans or an oracle. The goal is to optimize this labeling process and achieve higher accuracy with fewer labeled data points. Active learning has gained widespread attention recently due to its potential for reducing cos...")
14:38, 27 February 2023 Alpha5 talk contribs created page Action (Created page with "{{see also|Machine learning terms}} ==Introduction== Machine learning is an interdisciplinary field of study that involves the creation of algorithms that enable computer systems to learn and improve from experience. In this context, an action refers to a decision made by an agent based on available information at any given point in time. Machine learning involves agents taking actions based on observations of their environment. The goal is for the agent to learn how to...")
14:33, 27 February 2023 Alpha5 talk contribs created page A/B testing (Created page with "{{see also|Machine learning terms}} ==Introduction== A/B testing is a statistical method employed in machine learning research to compare two versions of a product and determine which version is more successful. It involves randomly dividing a population into two groups, "A" and "B," then exposing each group to one version of the tested product. After analyzing the results of this experiment, one version will be determined as having higher click-through rates or conversi...")
18:07, 26 February 2023 Alpha5 talk contribs created page Google Cloud terms (Redirected page to Machine learning terms/Google Cloud) Tag: New redirect
18:06, 26 February 2023 Alpha5 talk contribs created page TensorFlow terms (Redirected page to Machine learning terms/TensorFlow) Tag: New redirect