Understanding the mechanisms behind decisions taken by large foundation models in sequential decision making tasks is critical to ensuring that such systems operate transparently and safely. In this work, we perform exploratory analysis on the Video PreTraining (VPT) Minecraft playing agent, one of the largest open-source vision-based agents. We aim to illuminate its reasoning mechanisms by applying various interpretability techniques. First, we analyze the attention mechanism while the agent solves its training task - crafting a diamond pickaxe. The agent pays attention to the last four frames and several key-frames further back in its six-second memory. This is a possible mechanism for maintaining coherence in a task that takes 3-10 minutes, despite the short memory span. Secondly, we perform various interventions, which help us uncover a worrying case of goal misgeneralization: VPT mistakenly identifies a villager wearing brown clothes as a tree trunk when the villager is positioned stationary under green tree leaves, and punches it to death.

We introduce a new Bayesian admixture model intended for exploratory analysis of communication networks--specifically, the discovery and visualization of topic-specific subnetworks in email data sets. Our model produces principled visualizations of email networks, i.e., visualizations that have precise mathematical interpretations in terms of our model and its relationship to the observed data. We validate our modeling assumptions by demonstrating that our model achieves better link prediction performance than three state-of-the-art network models and exhibits topic coherence comparable to that of latent Dirichlet allocation. We showcase our model's ability to discover and visualize topic-specific communication patterns using a new email data set: the New Hanover County email network. We provide an extensive analysis of these communication patterns, leading us to recommend our model for any exploratory analysis of email networks or other similarly-structured communication data. Finally, we advocate for principled visualization as a primary objective in the development of new network models.

This paper explores the integration of two AI subdisciplines employed in the development of artificial agents that exhibit intelligent behavior: Large Language Models (LLMs) and Cognitive Architectures (CAs). We present three integration approaches, each grounded in theoretical models and supported by preliminary empirical evidence. The modular approach, which introduces four models with varying degrees of integration, makes use of chain-of-thought prompting, and draws inspiration from augmented LLMs, the Common Model of Cognition, and the simulation theory of cognition. The agency approach, motivated by the Society of Mind theory and the LIDA cognitive architecture, proposes the formation of agent collections that interact at micro and macro cognitive levels, driven by either LLMs or symbolic components. The neuro-symbolic approach, which takes inspiration from the CLARION cognitive architecture, proposes a model where bottom-up learning extracts symbolic representations from an LLM layer and top-down guidance utilizes symbolic representations to direct prompt engineering in the LLM layer. These approaches aim to harness the strengths of both LLMs and CAs, while mitigating their weaknesses, thereby advancing the development of more robust AI systems. We discuss the tradeoffs and challenges associated with each approach.

We introduce a joint model of network content and context designed for exploratory analysis of email networks via visualization of topic-specific communication patterns. Our model is an admixture model for text and network attributes which uses multinomial distributions over words as mixture components for explaining text and latent Euclidean positions of actors as mixture components for explaining network attributes. We demonstrate the capability of our model for descriptive, explanatory, and exploratory analysis by investigating the inferred topic-specific communication patterns of a new government email dataset, the New Hanover County email corpus.

Originally published on Towards AI the World's Leading AI and Technology News and Media Company. If you are building an AI-related product or service, we invite you to consider becoming an AI sponsor. At Towards AI, we help scale AI and technology startups. Let us help you unleash your technology to the masses. It's free, we don't spam, and we never share your email address.

Co-clustering is a class of unsupervised data analysis techniques that extract the existing underlying dependency structure between the instances and variables of a data table as homogeneous blocks. Most of those techniques are limited to variables of the same type. In this paper, we propose a mixed data co-clustering method based on a two-step methodology. In the first step, all the variables are binarized according to a number of bins chosen by the analyst, by equal frequency discretization in the numerical case, or keeping the most frequent values in the categorical case. The second step applies a co-clustering to the instances and the binary variables, leading to groups of instances and groups of variable parts. We apply this methodology on several data sets and compare with the results of a Multiple Correspondence Analysis applied to the same data.

It is no longer enough to build models that make accurate predictions. We also need to make sure that those predictions are fair. Doing so will reduce the harm of biased predictions. As a result, you will go a long way in building trust in your AI systems. To correct bias we need to start by analysing fairness in data and models. You can see a summary of the approaches we will cover below. Understanding why a model is unfair is more complicated. This is why we will first do an exploratory fairness analysis. This will help you identify potential sources of bias before you start modelling. We will then move on to measuring fairness. This is done by applying different definitions of fairness. We will discuss the theory behind these approaches. Along the way, we will also be applying them using Python. We will discuss key pieces of code and you can find the full project on GitHub. You should still be able to follow the article even if you do not want to use the Python code.

The worlds of AI and BI occupy distinct places in the analytics continuum, which is most often understood with concepts like descriptive analytics, predictive analytics, and prescriptive analytics. Users can leverage descriptive analytics and BI tools to explore what happened in the past, while predictive analytics makes use of ML models trained on real-world data to generate an educated guess about what will happen next. However, the lines separating these two camps are getting more blurry by the month. For years, Gartner has talked about how BI tool vendors are adding more ML and AI capabilities to their wares. In its latest Magic Quadrant for Analytics and BI Platforms, the firm talked about how the next generation of "augmented analytic" products will bring ML and AI to bear on things like data prep, query generation, and insight generation.

Natural Language Processing (NLP) is a subfield of computer science, artificial intelligence, information engineering, and human-computer interaction. This field focuses on how to program computers to process and analyze large amounts of natural language data. It is difficult to perform as the process of reading and understanding languages is far more complex than it seems at first glance. You are predicting whether a given tweet is about a real disaster or not. If not, predict a 0. Before we begin with anything else, let's check the class distribution.

If you want to learn more about exploratory analysis using Pandas, check out Simplilearn's Data Science with Python video, which can help. We can see that columns like LoanAmount and ApplicantIncome contain some extreme values. We need to process this data using data wrangling techniques to normalize and standardize the data. We will now take a look at data wrangling using Pandas as a part of our learning of Data Science with Python. Data wrangling refers to the process of cleaning and unifying messy and complicated data sets.