Difference between negative five and minus five

source link: http://mathforum.org/library/drmath/view/61346.html
In English it is not uncommon to hear "negative 5" called "minus 5."  
This is technically incorrect, but if you're not speaking with 
mathematicians, then it's acceptable to just use "minus 5."
 
A long, long time ago, people thought only in terms of the natural 
numbers:

  1, 2, 3, 4, 5, ...

You can do a lot with the natural numbers. You can count how many 
sheep, dollars, children, and friends you have. You can count how many 
apples you have. You can even do simple arithmetic: if you have 6 
apples and you lose half (divided by 2), you end up with 3 apples; if 
you have 6 apples and you double the number (times 2), you end up with 
12 apples; if you have 6 apples and you get two more (plus 2), you 
have 8; if you have 6 apples and you lose two (minus 2), you have 4.

The idea of subtraction (or minus) has been around since the days 
before fractions and integers, when people only thought in natural 
numbers.

If I say "nine, five" to you, all I have done is list two numbers:

  9, 5

I haven't told you anything about what to do with those numbers. The 
most you can do is just remember them. You don't know whether I want 
you to multiply them, divide them, add them, or just remember both of 
them (one could be the number of oranges I have and the other the 
number of cousins I have).

If I say "nine plus five" to you, then I have told you to add two 
numbers. You don't have to remember 9 and 5, you just have to know 
that the answer is 14.

Somewhere along the line, some people came up with zero (and that was 
a big deal) and some other people came up with fractions (and that was 
a big deal). Then some other people came up with integers. Integers 
are all the positive (natural) numbers, and zero, and the negative 
numbers:

  ..., -3, -2, -1, 0, 1, 2, 3, ...

It's hard to think of apples and sheep in terms of negative numbers, 
but they are useful in thinking about money and other things. For 
example, right now, my bank account has a negative amount of money in 
it.

Negative numbers are just a kind of number, not really any different 
from positive numbers.

If I say "nine negative five" to you, all I have done is list two 
numbers:

  9, -5

I haven't told you anything about what to do with those numbers. The 
most you can do is just remember them. You don't know whether I want 
you to multiply them, divide them, add them, or just remember both of 
them (one could be the balance in my friend's bank account and the 
other the balance in my bank account).

If I say "nine minus five" to you, then I have told you to subtract 5 
from 9. You don't have to remember 9 and 5, you just have to know that 
the answer is 4.

So "negative 5" is a number and "minus 5" is a mathematical operation 
you can do to another number. If it helps, you can think of "negative 
5" as a noun, as in the sentence "negative 5 is my least favorite 
number"; and you can think of "minus 5" as a verb as in the 
(ungrammatical) sentence "I want you to take 9 and minus 5 it."

One other thing. This tends to get complicated when you start doing 
crazy things like:

  "negative 5 plus 6"
or
  "8 minus negative 5"

If you want, you can check out this page for my suggestions of how to 
deal with this:

   Tips for Negative and Positive Numbers
   http://mathforum.org/library/drmath/view/57873.html 

I should note that I'm a bit sloppy with the distinction between 
"minus" and "negative" on that page.

For the last part of your question, the list you gave reads:

  "positive three" OR "three"
  "negative seven"
  "negative three-fourths"
  "negative five point four"
  "one fourth" OR "one quarter"

Hope this helps.  If you have other questions about this or anything 
else, please write back.

- Doctor Achilles, The Math Forum
  http://mathforum.org/dr.math/ 

深度学习是机器学习的一个子领域,它基于人工神经网络的研究,特别是利用多层次的神经网络来进行学习和模式识别。深度学习模型能够学习数据的高层次特征,这些特征对于图像和语音识别、自然语言处理、医学图像分析等应用至关重要。以下是深度学习的一些关键概念和组成部分: 1. **神经网络(Neural Networks)**:深度学习的基础是人工神经网络,它是由多个层组成的网络结构,包括输入层、隐藏层和输出层。每个层由多个神经元组成,神经元之间通过权重连接。 2. **前馈神经网络(Feedforward Neural Networks)**:这是最常见的神经网络类型,信息从输入层流向隐藏层,最终到达输出层。 3. **卷积神经网络(Convolutional Neural Networks, CNNs)**:这种网络特别适合处理具有网格结构的数据,如图像。它们使用卷积层来提取图像的特征。 4. **循环神经网络(Recurrent Neural Networks, RNNs)**:这种网络能够处理序列数据,如时间序列或自然语言,因为它们具有记忆功能,能够捕捉数据中的时间依赖性。 5. **长短期记忆网络(Long Short-Term Memory, LSTM)**:LSTM 是一种特殊的 RNN,它能够学习长期依赖关系,非常适合复杂的序列预测任务。 6. **生成对抗网络(Generative Adversarial Networks, GANs)**:由两个网络组成,一个生成器和一个判别器,它们相互竞争,生成器生成数据,判别器评估数据的真实性。 7. **深度学习框架**:如 TensorFlow、Keras、PyTorch 等,这些框架提供了构建、训练和部署深度学习模型的工具和库。 8. **激活函数(Activation Functions)**:如 ReLU、Sigmoid、Tanh 等,它们在神经网络中用于添加非线性,使得网络能够学习复杂的函数。 9. **损失函数(Loss Functions)**:用于评估模型的预测与真实值之间的差异,常见的损失函数包括均方误差(MSE)、交叉熵(Cross-Entropy)等。 10. **优化算法(Optimization Algorithms)**:如梯度下降(Gradient Descent)、随机梯度下降(SGD)、Adam 等,用于更新网络权重,以最小化损失函数。 11. **正则化(Regularization)**:技术如 Dropout、L1/L2 正则化等,用于防止模型过拟合。 12. **迁移学习(Transfer Learning)**:利用在一个任务上训练好的模型来提高另一个相关任务的性能。 深度学习在许多领域都取得了显著的成就,但它也面临着一些挑战,如对大量数据的依赖、模型的解释性差、计算资源消耗大等。研究人员正在不断探索新的方法来解决这些问题。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值