value
In investing, the intrinsic economic worth of an asset based on its ability to generate cash flows discounted to present value; distinct from 'price' which is what the market charges
As defined in Aswath Damodaran: I Am More Cautious Than Ever
Where it comes up · 2
- Illustrated Guide to Transformers Neural Network: A step by step explanation10 claims
- Aswath Damodaran: I Am More Cautious Than Ever5 claims
Most important claims · 10 of 15Search all claims for “value” →
- To achieve self-attention, the input is fed into three distinct fully connected layers to create query, key, and value vectors, which follow the same concept as a retrieval system where queries are mapped against keys to find relevant matches.Illustrated Guide to Transformers Neural Network: A step by step explanation
- Transformers must add positional encoding information to input embeddings because unlike recurrent neural networks, transformers have no recurrence and therefore need explicit position information to understand word order.Illustrated Guide to Transformers Neural Network: A step by step explanation
- The attention scores are scaled down by dividing them by the square root of the dimension of the queries and keys in order to allow for more stable gradients, as multiplying values can have exploding effects.Illustrated Guide to Transformers Neural Network: A step by step explanation
- Dividends and buybacks are equivalent sources of cash flow to equity investors; both should be counted equally in valuation because whether dividends or buybacks reach your pocket depends on whether you sell shares or hold, making the choice between them a matter of corporate governance preference, not fundamental cash flow value.Aswath Damodaran: I Am More Cautious Than Ever
- Multi-headed attention involves splitting the query, key, and value vectors into multiple sub-vectors before applying self-attention, where each split undergoes the same self-attention process as a separate 'head' that learns different attention representations.Illustrated Guide to Transformers Neural Network: A step by step explanation
- In the decoder's second multi-headed attention layer, the encoder's outputs serve as queries and keys while the first multi-headed attention layer's outputs serve as values, allowing the decoder to decide which encoder inputs are relevant to focus on.Illustrated Guide to Transformers Neural Network: A step by step explanation
- Word embedding layers function as lookup tables that map each word to a vector with continuous values representing that word, since neural networks learn through numbers and cannot directly process words.Illustrated Guide to Transformers Neural Network: A step by step explanation
- Private credit has grown to multi-trillion-dollar scale despite never clearly answering what unique need or niche it fills beyond what banks and corporate bond markets already provide; this lack of clear value proposition makes large-scale growth dangerous.Aswath Damodaran: I Am More Cautious Than Ever
- The attention weights from softmax are multiplied by the value vector to produce an output vector, where higher softmax scores preserve the value of words the model has learned to prioritize as important, while lower scores drown out irrelevant words.Illustrated Guide to Transformers Neural Network: A step by step explanation
- Gold cannot be valued (only priced) because it has no cash flows; gold pricing is driven by three factors: inflation hedging, crisis hedging, and opportunity cost (interest rates), making it a demand/supply-driven asset class.Aswath Damodaran: I Am More Cautious Than Ever