New pages
- 19:18, 9 July 2024 Loss function (hist | edit) [5,213 bytes] Mr. MacKenty (talk | contribs) (Created page with "''This answer was supported by a LLM'' '''Loss Function''' A loss function, also known as a cost function or objective function, is a mathematical function used in machine learning to measure the difference between the predicted output of a model and the actual target values. The primary goal of training a model is to minimize the loss function, thereby improving the model’s accuracy. Here’s a detailed explanation of loss functions within the context of a chatbot s...")
- 19:15, 9 July 2024 Long short-term memory (LSTM) (hist | edit) [5,662 bytes] Mr. MacKenty (talk | contribs) (Created page with "''This answer was supported by a LLM'' '''Long Short-Term Memory (LSTM)''' Long Short-Term Memory (LSTM) is a type of recurrent neural network (RNN) architecture designed to handle long-term dependencies and mitigate issues such as vanishing and exploding gradients, which are common in traditional RNNs. LSTMs are particularly effective in tasks that involve sequential data, such as language modeling and time series prediction. Here’s a detailed explanation of LSTMs w...")
- 19:13, 9 July 2024 Latency (hist | edit) [5,029 bytes] Mr. MacKenty (talk | contribs) (Created page with "''This answer was supported by a LLM'' '''Latency''' Latency refers to the time delay between a user's action and the system's response. In the context of a chatbot system, latency is a critical factor that affects user experience and the perceived responsiveness of the chatbot. Here’s a detailed explanation of latency within the context of a chatbot system: == Definition == * '''Latency''': * The time delay between the input (user query) and the output (chatbot r...")
- 18:02, 9 July 2024 Large language model (LLM) (hist | edit) [5,182 bytes] Mr. MacKenty (talk | contribs) (Created page with "''This answer was supported by a LLM'' '''Large Language Model (LLM)''' A Large Language Model (LLM) is a type of artificial intelligence model that has been trained on vast amounts of text data to understand, generate, and manipulate human language. LLMs leverage advanced machine learning techniques, particularly deep learning, to perform a wide range of natural language processing (NLP) tasks. Here’s a detailed explanation of LLMs within the context of a chatbot sy...")
- 18:00, 9 July 2024 Hyperparameter tuning (hist | edit) [5,610 bytes] Mr. MacKenty (talk | contribs) (Created page with "```mediawiki ''This answer was supported by a LLM'' '''Hyperparameter Tuning''' Hyperparameter tuning is the process of optimizing the hyperparameters of a machine learning model to improve its performance. Unlike model parameters, which are learned during training, hyperparameters are set before the training process begins and directly influence the behavior of the learning algorithm. Here’s a detailed explanation of hyperparameter tuning within the context of a cha...")
- 08:59, 3 July 2024 Graphical processing unit (GPU) (hist | edit) [5,138 bytes] Mr. MacKenty (talk | contribs) (Created page with "''This answer was supported by a LLM'' '''Graphical Processing Unit (GPU)''' A Graphical Processing Unit (GPU) is a specialized electronic circuit designed to accelerate the processing of images and videos. It has become essential for deep learning and other computationally intensive tasks due to its ability to perform many calculations simultaneously. Here’s a detailed explanation of GPUs within the context of a chatbot system: == Definition == * '''Graphical Proce...")
- 08:55, 3 July 2024 Dataset (hist | edit) [4,918 bytes] Mr. MacKenty (talk | contribs) (Created page with "''This answer was supported by a LLM'' '''Dataset''' A dataset is a structured collection of data used for various purposes such as training, validating, and testing machine learning models, including chatbots. Datasets can consist of various types of data, such as text, images, audio, or numerical values, depending on the application. Here’s a detailed explanation of a dataset within the context of a chatbot system: == Definition == * '''Dataset''': * A collectio...")
- 08:54, 3 July 2024 Selection (hist | edit) [4,506 bytes] Mr. MacKenty (talk | contribs) (Created page with " ''This answer was supported by a LLM'' '''Sampling Bias''' Sampling bias occurs when the sample selected for analysis is not representative of the entire population, leading to skewed or inaccurate results. This type of bias can significantly impact the performance and fairness of AI systems, including chatbots. Here’s a detailed explanation of sampling bias within the context of a chatbot system: == Definition == * '''Sampling Bias''': * A type of bias that aris...")
- 08:53, 3 July 2024 Sampling (hist | edit) [4,615 bytes] Mr. MacKenty (talk | contribs) (Created page with " ''This answer was supported by a LLM'' '''Sampling''' Sampling is the process of selecting a subset of data from a larger dataset to train machine learning models, including chatbots. The goal of sampling is to create a representative subset that accurately reflects the characteristics of the entire dataset. Here’s a detailed explanation of sampling within the context of a chatbot system: == Definition == * '''Sampling''': * The technique of choosing a smaller, m...")
- 08:52, 3 July 2024 Linguistic (hist | edit) [4,314 bytes] Mr. MacKenty (talk | contribs) (Created page with " ''This answer was supported by a LLM'' '''Linguistic Bias''' Linguistic bias refers to prejudice or favoritism toward certain languages, dialects, or ways of speaking within AI systems. This type of bias can impact the performance and fairness of chatbots and other language-based technologies. Here’s a detailed explanation of linguistic bias within the context of a chatbot system: == Definition == * '''Linguistic Bias''': * Bias that occurs when AI systems favor...")
- 08:51, 3 July 2024 Labelling (hist | edit) [4,208 bytes] Mr. MacKenty (talk | contribs) (Created page with " ''This answer was supported by a LLM'' '''Labelling Bias''' Labelling bias occurs when the labels assigned to training data reflect subjective judgments, stereotypes, or prejudices, rather than objective truth. This type of bias can significantly impact the performance and fairness of AI systems, including chatbots. Here’s a detailed explanation of labelling bias within the context of a chatbot system: == Definition == * '''Labelling Bias''': * Bias introduced du...")
- 08:49, 3 July 2024 Historical (hist | edit) [4,070 bytes] Mr. MacKenty (talk | contribs) (Created page with " ''This answer was supported by a LLM'' Historical bias refers to distortions or inaccuracies in data that arise from historical inequalities, prejudices, or systemic discrimination embedded within the data. This type of bias can significantly affect the training and performance of AI systems, including chatbots. Here’s a detailed explanation of historical bias within the context of a chatbot system: == Definition == * '''Historical Bias''': * Bias in data that re...")
- 08:48, 3 July 2024 Confirmation (hist | edit) [3,758 bytes] Mr. MacKenty (talk | contribs) (Created page with " ''This answer was supported by a LLM'' Confirmation, often referred to as confirmation bias, is the tendency to search for, interpret, and remember information in a way that confirms one’s preexisting beliefs or hypotheses. This cognitive bias can significantly affect decision-making processes and the development of AI systems. Here’s a detailed explanation of confirmation within the context of a chatbot system: == Definition == * '''Confirmation Bias''': * Th...")
- 08:44, 3 July 2024 Biases (hist | edit) [4,575 bytes] Mr. MacKenty (talk | contribs) (Created page with "This article was created with the help and support of an LLM Bias refers to a systematic error or deviation from true values or fairness that affects data, models, and decision-making processes. In the context of machine learning and artificial intelligence, bias can lead to skewed results and unfair treatment of certain groups. Here’s a detailed explanation of bias within the context of a chatbot system: == Types of Bias == * '''Data Bias''': * Occurs when the tr...")
- 08:40, 3 July 2024 Bag-of-words (hist | edit) [3,657 bytes] Mr. MacKenty (talk | contribs) (Created page with "This wiki article was made with the help and support of an LLM ```mediawiki '''Bag of Words (BoW)''' Bag of Words (BoW) is a fundamental technique used in natural language processing (NLP) and information retrieval to represent text data in a structured format. It simplifies the text data by treating it as a collection of individual words, disregarding grammar and word order, but keeping track of word frequency. Here’s a detailed explanation of BoW within the context...")
- 08:38, 3 July 2024 Backpropagation through time (BPTT) (hist | edit) [3,480 bytes] Mr. MacKenty (talk | contribs) (Created page with "Backpropagation Through Time (BPTT) is an extension of the backpropagation algorithm for training recurrent neural networks (RNNs). RNNs are designed to handle sequential data by maintaining a state that can capture information from previous inputs. However, training RNNs is challenging due to their complex structure and the need to account for dependencies over time. Here’s a detailed explanation of BPTT within the context of a chatbot system: 1. Sequential Nature o...")
- 08:33, 3 July 2024 Chat bots (hist | edit) [976 bytes] Mr. MacKenty (talk | contribs) (Created page with "right|frame|Case study notes<ref>http://www.flaticon.com/</ref> * Backpropagation through time (BPTT) * Bag-of-words * Biases * Confirmation * Historical * Labelling * Linguistic * Sampling * Selection * Dataset * Deep learning * Graphical processing unit (GPU) * Hyperparameter tuning * Large language model (LLM) * Latency * Long short-term memory (LSTM) * Loss function * Memory...")
- 08:28, 3 July 2024 2025 case study (hist | edit) [1,388 bytes] Mr. MacKenty (talk | contribs) (Created page with "right|frame|Case study<ref>http://www.flaticon.com/</ref> == Introduction == Higher-level students must write 3 papers. The case study is the third paper. Every year the case study discusses a different topic. Students must become '''very familiar''' with the case study. The IB recommends spending about a year studying this case study. This page will help you organize and understand the 2024 case study. == The case study == Media:D 4 c...")
