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).

23:31, 25 February 2023 Alpha5 talk contribs created page Training loss (Created page with "{{see also|Machine learning terms}} ==Introduction== Training loss is an important metric in machine learning that measures the discrepancy between predicted output and actual output. It helps evaluate a model's performance during training, with the aim being to minimize this loss so that it can generalize well on unseen data. ==Types of Loss Functions== Machine learning employs a variety of loss functions, depending on the problem being solved and the model being emplo...")
14:30, 25 February 2023 Alpha5 talk contribs created page Training-serving skew (Created page with "{{see also|Machine learning terms}} ===Training-Serving Skew in Machine Learning== Training-serving skew is a common issue when deploying machine learning models, particularly in production settings where they will be put to real world use. This term describes the difference in performance of a model during training and deployment that can arise from various sources such as different data distributions, hardware configurations or software dependencies between these envir...")
14:03, 25 February 2023 Alpha5 talk contribs created page L0 regularization (Created page with "{{see also|Machine learning terms}} ==Introduction== L0 regularization, also referred to as the "feature selection" regularization, is a machine learning technique used to encourage models to utilize only some of the available features from data. It does this by adding a penalty term to the loss function that encourages models to have sparse weights - that is, weights close to zero. The goal of L0 regularization is to reduce feature counts used by the model which improve...")
13:52, 25 February 2023 Alpha5 talk contribs created page Stability (Created page with "==Introduction== Stability in machine learning refers to the robustness and dependability of a model's performance when exposed to small variations in training data, hyperparameters, or even the underlying data distribution. This is an essential aspect to consider when building models for real-world applications since even small changes can drastically impact predictions made by the model. ==Types of Stability== In machine learning, there are...")
13:46, 25 February 2023 Alpha5 talk contribs created page Stable (Redirected page to Stability) Tag: New redirect
13:40, 25 February 2023 Alpha5 talk contribs created page Unstable (Redirected page to Stability) Tag: New redirect
12:38, 25 February 2023 Alpha5 talk contribs created page Iteration (Created page with "{{see also|Machine learning terms}} ===Iteration in Machine Learning== Machine learning is a subfield of artificial intelligence that seeks to develop algorithms and statistical models that can learn from data and make predictions or decisions based on it. One key concept in machine learning is iteration; this concept helps ensure success when applying the learned algorithm or model. Iteration is the process of repeating a task multiple times to improve outcomes. In mac...")
12:18, 25 February 2023 Alpha5 talk contribs created page Interpretability (Created page with "{{see also|Machine learning terms}} ===Interpretability in Machine Learning== Interpretability in machine learning refers to the process of comprehending and explaining the actions taken by a model. It plays an essential role in developing these models, particularly in fields such as healthcare, finance and criminal justice where decisions made by these algorithms may have far-reaching repercussions for individuals and society at large. Interpretability is the goal of i...")
21:11, 24 February 2023 Alpha5 talk contribs created page LLaMA (Created page with "{{see also|LLaMA/Model Card}} {{:LLaMA/Model Card}}")
21:09, 24 February 2023 Alpha5 talk contribs moved page LLaMA to LLaMA/Model Card without leaving a redirect
19:52, 24 February 2023 Alpha5 talk contribs created page LLaMA (Created page with "==Model details== Organization developing the model The FAIR team of Meta AI. Model date LLaMA was trained between December. 2022 and Feb. 2023. Model version This is version 1 of the model. Model type LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters. Paper or resources for more information More information can be found in the paper “LLaMA, Open and Efficient Found...")
19:16, 24 February 2023 Alpha5 talk contribs created page Input layer (Created page with "{{see also|Machine learning terms}} ==Introduction== The input layer is an essential element in any machine learning model. It takes input data and passes it on to the next layer in the model, where it is processed and transformed into meaningful information. In this article, we'll examine in depth the characteristics of an input layer as well as its role in overall machine learning model operation. ==Structure of the Input Layer== The input layer is typically the initi...")
18:43, 24 February 2023 Alpha5 talk contribs created page SL (Redirected page to Supervised learning) Tag: New redirect
18:42, 24 February 2023 Alpha5 talk contribs created page UL (Redirected page to Unsupervised learning) Tag: New redirect
18:36, 24 February 2023 Alpha5 talk contribs created page IID (Redirected page to Independently and identically distributed (i.i.d.)) Tag: New redirect
18:36, 24 February 2023 Alpha5 talk contribs created page I.i.d. (Redirected page to Independently and identically distributed (i.i.d.)) Tag: New redirect
18:36, 24 February 2023 Alpha5 talk contribs created page Independently and identically distributed (Redirected page to Independently and identically distributed (i.i.d.)) Tag: New redirect
18:36, 24 February 2023 Alpha5 talk contribs created page Independently and identically distributed (i.i.d.) (Created page with "{{see also|Machine learning terms}} ==Introduction== Machine learning algorithms often make the assumption of independently and identically distributed (i.i.d.) data, which implies each data point is drawn independently from a given probability distribution. This assumption is essential for many machine learning algorithms as it permits powerful mathematical operations to make predictions based on observed patterns in the data. ==Definition of i.i.d. data== Formally spe...")
18:31, 24 February 2023 Alpha5 talk contribs created page NN (Redirected page to Neural network) Tag: New redirect
18:31, 24 February 2023 Alpha5 talk contribs created page ANN (Redirected page to Neural network) Tag: New redirect
18:27, 24 February 2023 Alpha5 talk contribs moved page Online to Online learning
17:27, 24 February 2023 Alpha5 talk contribs created page Inference (Created page with "{{see also|Machine learning terms}} ===Definition of Inference in Machine Learning== Machine learning refers to the process of inference, or making predictions or decisions based on data and a trained model. The goal is for the model to generate outputs as accurate as possible given its input data, then use these outputs to make decisions or predictions about new, unseen data. ==Types of Inference in Machine Learning== In machine learning, there are two primary forms of...")
12:23, 24 February 2023 Alpha5 talk contribs created page Hyperparameters (Redirected page to Hyperparameter) Tag: New redirect
12:21, 24 February 2023 Alpha5 talk contribs created page Hyperparameter (Created page with "{{see also|Machine learning terms}} ===Introduction== Machine learning involves finding the optimal set of parameters that allows the model to make accurate predictions on new data. Unfortunately, certain parameters cannot be learned from training data and must be set before training the model - these are known as hyperparameters - which play a significant role in determining its performance. ==Definition== Hyperparameters are parameters set before training a machine le...")
12:15, 24 February 2023 Alpha5 talk contribs created page Actual output (Redirected page to Label) Tag: New redirect
12:13, 24 February 2023 Alpha5 talk contribs created page Biases (Redirected page to Bias) Tag: New redirect
12:00, 24 February 2023 Alpha5 talk contribs created page Hidden layer (Created page with "{{see also|Machine learning terms}} ===Introduction== Machine learning relies on neural networks, which are capable of learning from large datasets to detect patterns and make predictions. Neural networks consist of multiple layers connected nodes where each node performs a simple mathematical operation on its inputs. The output from one layer feeds into the next until an ultimate prediction is produced. Hidden layers play an integral role in these neural networks and pl...")
11:54, 24 February 2023 Alpha5 talk contribs created page Mislabel (Redirected page to Label) Tag: New redirect
11:53, 24 February 2023 Alpha5 talk contribs created page Biased (Redirected page to Bias) Tag: New redirect
11:53, 24 February 2023 Alpha5 talk contribs created page Noisy (Redirected page to Noise) Tag: New redirect
11:45, 24 February 2023 Alpha5 talk contribs created page Ground truth (Created page with "{{see also|Machine learning terms}} ===Introduction== Machine learning is a rapidly developing field that seeks to create algorithms and models that can learn from data to make predictions or decisions. For these models to be accurate, they need to be trained on high-quality data - including "ground truth." Ground truth is a key concept in machine learning, defined as accurate and reliable information about the target variable or phenomenon being learned by the model. T...")
16:35, 23 February 2023 Alpha5 talk contribs created page Gradient descent (Created page with "{{see also|Machine learning terms}} ===Introduction== Gradient descent is a popular optimization algorithm in machine learning. It works by finding the minimum cost function, which can be adjusted to minimize errors between predicted output and actual output from a model. Gradient descent utilizes weights and biases as input parameters to achieve this minimal error margin. ==How Gradient Descent Works== Gradient descent works by iteratively altering the parameters of a...")
14:52, 23 February 2023 Alpha5 talk contribs created page Generalization (Created page with "{{see also|Machine learning terms}} ===Introduction== Machine learning is a subfield of artificial intelligence that involves developing algorithms and statistical models to make predictions or decisions based on data. One key challenge in machine learning lies in creating models that can generalize well to new data sets, meaning they can accurately forecast outcomes from unknown datasets. In this article, we will examine the concept of generalization in machine learnin...")
07:27, 23 February 2023 Alpha5 talk contribs created page Generalization curve (Created page with "{{see also|Machine learning terms}} ===Introduction== Machine learning strives to build models that accurately predict unseen data. To do this, machine learning models are trained on a dataset consisting of input features and their corresponding target values. Unfortunately, the performance of the model on this training dataset does not guarantee its performance when faced with new information - known as overfitting. To address this issue, evaluation of the model's perfo...")
06:33, 23 February 2023 Alpha5 talk contribs created page Feedback loop (Created page with "{{see also|Machine learning terms}} ===Introduction== Feedback loops are crucial components of many machine learning algorithms, as they offer models a way to learn and improve over time. In this article, we'll define what feedback loops are, how they function within machine learning algorithms, and why they're so important. ==What is a feedback loop?== A feedback loop is a systemic mechanism in which an input is processed and an output produced. This output then serves...")
06:23, 23 February 2023 Alpha5 talk contribs created page File:Mnist 5 example1.png (File uploaded with MsUpload)
06:23, 23 February 2023 Alpha5 talk contribs uploaded File:Mnist 5 example1.png (File uploaded with MsUpload)
06:23, 23 February 2023 Alpha5 talk contribs uploaded File:Mnist example1.png (File uploaded with MsUpload)
06:23, 23 February 2023 Alpha5 talk contribs created page File:Mnist example1.png (File uploaded with MsUpload)
03:42, 23 February 2023 Alpha5 talk contribs created page Feature vector (Created page with "{{see also|Machine learning terms}} ===Introduction== Machine learning utilizes feature vectors, which are numerical values that describe an object or phenomenon. A feature vector may be defined as an n-dimensional array of numerical features representing a data point or example. As an array of feature values that represent an example, feature vector is used in training the model and using the model to make predictions (inferen...") Tag: Visual edit: Switched
21:59, 22 February 2023 Alpha5 talk contribs created page Sensitivity (Redirected page to True positive rate (TPR)) Tag: New redirect
20:58, 22 February 2023 Alpha5 talk contribs created page Z-score normalization (Created page with "{{see also|Machine learning terms}} ===Introduction== Data normalization in machine learning is a critical preprocessing step that helps boost the performance of many algorithms. Normalization involves scaling data to a specified range or distribution to reduce the impact of differences in scale or units of features. One widely-used technique for normalization is Z-score normalization (also referred to as standardization). ==What is Z-score normalization?== Z-score norm...")
15:37, 22 February 2023 Alpha5 talk contribs created page Weighted sum (Created page with "{{see also|Machine learning terms}} ===Introduction== In machine learning, a weighted sum is an algorithmic mathematical operation used to combine multiple input values by assigning weights to each. It's fundamental in many machine learning algorithms such as linear regression, neural networks and decision trees; this transformation transforms input data into one single output value which can then be used for prediction or classification purposes. ==Definition of Weight...")
15:27, 22 February 2023 Alpha5 talk contribs created page Weights (Redirected page to Weight) Tag: New redirect
14:41, 22 February 2023 Alpha5 talk contribs created page Weight (Created page with "{{see also|Machine learning terms}} ===Introduction== Machine learning uses weight as a fundamental concept to represent the strength of connections between nodes in a neural network. These connections form the basis for models' capacity to make accurate predictions and classifications by learning patterns from data. Understanding how weights are allocated and adjusted is essential in comprehending how a neural network functions. ==What is weight?== Machine learning ass...")
14:18, 22 February 2023 Alpha5 talk contribs created page Validation (Created page with "{{see also|Machine learning terms}} ===Introduction== Machine learning practitioners understand the importance of validation as one of the key steps in developing a predictive model. Validation measures the accuracy and dependability of a trained model by applying it to new data sets, with an aim of estimating its likely performance when applied. ==Training and Testing Data== Validating a machine learning model requires labeled data that can be used for training and tes...")
13:50, 22 February 2023 Alpha5 talk contribs created page Validation data set (Redirected page to Validation set) Tag: New redirect
13:49, 22 February 2023 Alpha5 talk contribs created page Validation data (Redirected page to Validation set) Tag: New redirect
13:49, 22 February 2023 Alpha5 talk contribs created page Validation set (Created page with "{{see also|Machine learning terms}} ===Introduction== Machine learning aims to construct predictive models that can accurately forecast new and unseen data. Training a machine learning model involves teaching it labeled data so it can learn patterns and relationships within it; however, after training the model, evaluation of its performance on unlabeled datasets must take place - this is where validation sets come into play. ==What is a validation set?== Validation set...")
13:28, 22 February 2023 Alpha5 talk contribs created page Validation loss (Created page with "{{see also|Machine learning terms}} ===Introduction== Validation loss in machine learning is a widely used metric to gauge the performance of models. It measures how well they can generalize their predictions to new data sets. In this article, we'll define validation loss and discuss its application to evaluating machine learning models. ==What is Validation Loss?== Validation loss is a metric that measures the performance of a machine learning model on a validation set...")