8

The term classical AI refers to the concept of intelligence that was broadly accepted after the Dartmouth Conference and basically refers to a kind of intelligence that is strongly symbolic and oriented to logic and language processing. One basic point is the duality body vs. mind. It's in this period that the mind starts to be compared with computer ...


5

This is something of an orthogonal answer, but I think Brooks didn't go about his idea the right way. That is, subsumption architecture is one in which the 'autopilot' is replaced by a more sophisticated system when necessary. (All pieces receive the raw sensory inputs, and output actions, some of which turn off or on other systems.) But a better approach ...


4

I believe you are referring to something that Arend Hintze wrote about in his article "Understanding the four types of AI, from reactive robots to self-aware beings". Here are the four types from his article: Type I AI: Reactive machines The most basic types of AI systems are purely reactive, and have the ability neither to form memories nor to use past ...


3

Catan is actually a much more complicated game than the simple rules would suggest, and an exact solution is probably beyond the scope of current AI techniques. Monte Carlo Tree Search or Expectiminimax techniques seem like they could help, but are intended for games of perfect information. Catan is not a game of perfect information (the development cards ...


3

Methodology bias is difficult to avoid, since we can only see the methodologies that have been developed to proof of concept. Time is a continuous horizon of bias breaking in research. ARPAnet, which is now the Internet, was designed to reduce the bias by narrowing the gap between research laboratories, but it does not bridge across time. Luger's book is ...


3

A nice example Markov Decision Processes, which can be solved by classic reinforcement learning techniques like Q learning. A Markov Decision Process consists of A set of discrete states (or continuous states that have been discretized) A set of possible actions that can be taken in each state. A set of transition probabilities that describe how an agent ...


3

I was hoping to see more answers here, but I'll get us started with some examples: Combinatorial Search Problems: If your problem can be phrased as movement through a combinatorial graph, you don't need a neural network. In particular, your problem should have discrete states, a clear set of actions that are possible in each state, a clear definition of ...


3

Welcome to AI.SE @Israr Ali. The problem of scheduling a timetable is an example of a constraint satisfaction problem, a topic long studied in AI. There are many possible techniques to apply to this kind of problem. They can be organized into three broad categories: Global search algorithms, like backtracking search can be used to try and find an ...


2

Although there seems to be an apt analogy between Gödel's theorems and the PSHH, there is nothing formal linking the two together. More concretely, Gödel's theorems are about systems that decide certain "truths" about mathematics, but unless I am mistaken, the PSSH doesn't imply that the symbol system of the mind needs to decide truths. Though implicitly ...


2

The PSSH is often attacked via either Godel's theorems or Turing's incomputability theorem. However, both attacks an implicit assumption: that to be intelligent is to be able to decide undecidable questions. It's really not clear that this is so. Consider what Godel's theorems say, in essence: "powerful" formal systems cannot prove, using only techniques ...


2

I'm not sure any intelligent mechanism can be entirely free of symbolic logic. Even where a decision is statistically based, a machine that takes actions must include some form of: IF {some condition} THEN {some action} As to the popularity of newly proven statistical AI methods (ANN and genetic algorithms), this derives from the greater utility they ...


2

You might also ask if there's any particular reason why we would use a neural net. If we're to train a neural net to play chess, we need to be able to: 1. Feed it positions as input vectors (easy enough), 2. Decide on an output format. Perhaps a distribution over possible moves (but then, how to represent that such that the meaning of a specific output cell ...


2

ANNs as used today need 1. a lot of data 2. a lot of computational power. Before we had any of the above two, we didn't really know how to properly build ANNs since we didn't quite have the means to train the network, and thus couldn't evaluate it. "Symbolic AI" on the other hand, is very much just a bunch of if-else/logical conditions, much like ...


2

If you're looking for AI systems: Deep Blue Eliza If you're looking for specific algorithms: Bayesian Networks Decision Trees Any search algorithm


2

Historically, the non-ML approach would be an expert system. This is typically a rules-based decision system, falling under the umbrella of symbolic AI. These systems can have strong utility in limited contexts, but are generally "brittle" in that parameters not previously defined or accounted will produce no-compute or weak utility. Because the rules of ...


2

Sure! There's the whole Semantic Web scene! OWL is derived from DLs and Frames, arguably has a lot in common with semantic networks too. Expert-driven decision support systems are still being developed (and researched) in industries where the human is required to take responsibility or getting data is not going to happen. As the ideas evolve so do the names. ...


2

Oh yeah, definitely. Just to pick one example, you have Douglas Hofstader's group at Indiana. I think most of what they do would fall under the rubric of GOFAI (or at least closer to that than the statistical machine learning stuff). Beyond that, just go to the CORR and browse around the AI category. You'll see plenty of neural networks and ...


2

I'll take a shot at answering this, though I'm no expert in Neural Nets or Deep Learning. Given that practical thought vectors (TVs) don't yet exist, and may be impractical or impossible, I think answering your question will require a lot of conjecture and speculation. So here goes... For thought vectors to be useful in or outside NNs, the vector values ...


2

Nice question! I think there are a couple of issues at work here. Is the historical weakness of GOFAI in relation to non-trivial combinatorial games partly a function of the structure of the games studied, where game states and token values cannot be precisely quantified? I think the short answer is yes. The real issue is in the last part: ...


1

The symbol grounding problem is about the meaning of symbols (semantics) in general. The extension of the concept to a physics engine would seem to be a new, specfic domain. From the paper's abstract: The development of complex interactive 3D systems raises the need for representations supporting more abstract descriptions of world objects, their ...


1

There are two factors that will change the ability of a deep neural network to fit a given dataset: either you need more data, or a deeper and wider network. Since the pattern is only 2-d, it can likely be approximated by some sort of simple periodic function. A DNN can approximate periodic functions pretty well, so the issue is probably that you don't have ...


1

XAI is relevant to "black box" AI (machine learning methods where the decision making rationale is not apparent, only the structure of the system that led to that decision.) Symbolic AI, GOFAI, and Expert Systems are both explainable and understood, in that the the decision-making process is designed by humans. (Symbolic AI involves human-readable ...


1

Statistical AI, arising from machine learning, tends to be more concerned with "inductive" thought: given a set of patterns, induce the trend. Classical AI is the branch of artificial intelligence research that concerns itself with attempting to explicitly represent human knowledge in a declarative form i.e given a set of constraints, deduce a conclusion. ...


1

Image Segmentation with Unsupervised Learning. Deep Learning is now widely used for image classification and segmentation. However, for segmentation, some algorithm are still really effective. They could be a great solution for the development of self-driving cars for examples. K-means for image segmentation. When you identify the pixels of an RGB image ...


1

A neural net with even a single hidden layer is capable of Universal function approximation - it can approximate any continuous function 'as closely as you like'. Hence, one option would be to look for GOFAI applications that would benefit from this property - for example, in state-space search approaches where the utility of a state is not readily defined ...


1

Sure! This is a somewhat hot area right now. There are lots of ways to do it. Probably the main line of research is with Bayesian Networks (1980's) and Casual Networks (1990's). These are basically rule-based systems for reasoning probabilistically. They rely on a user-designed model, which corresponds well to rules (e.g. when blood pressure is high, then ...


Only top voted, non community-wiki answers of a minimum length are eligible