Most Popular
1500 questions
6
votes
1 answer
How are continuous actions sampled (or generated) from the policy network in PPO?
I am trying to understand and reproduce the Proximal Policy Optimization (PPO) algorithm in detail. One thing that I find missing in the paper introducing the algorithm is how exactly actions $a_t$ are generated given the policy network…
Daniel B.
- 835
- 1
- 6
- 14
6
votes
1 answer
How to graphically represent a RNN architecture implemented in Keras?
I'm trying to create a simple blogpost on RNNs, that should give a better insight into how they work in Keras. Let's say:
model = keras.models.Sequential()
model.add(keras.layers.SimpleRNN(5, return_sequences=True, input_shape=[None,…
Mindaugas Bernatavičius
- 161
- 3
6
votes
2 answers
Are probabilistic models dead ends in AI?
I am a strong believer of Marvin Minsky's idea about Artificial General Intelligence (AGI) and one of his thoughts was that probabilistic models are dead ends in the field of AGI.
I would really like to know the thoughts and ideas of people who…
Parth Raghav
- 345
- 1
- 8
6
votes
1 answer
Why are "Transformers" called this way?
What is the reason behind the name "Transformers", for Multi Head Self-Attention-based neural networks from Attention is All You Need?
I have been googling this question for a long time, and nowhere I can find any explanation.
Leevo
- 305
- 2
- 9
6
votes
1 answer
What is the impact of scaling the KL divergence and reconstruction loss in the VAE objective function?
Variational autoencoders have two components in their loss function. The first component is the reconstruction loss, which for image data, is the pixel-wise difference between the input image and output image. The second component is the…
rich
- 171
- 1
- 6
6
votes
3 answers
How close have we come to passing the Turing Test?
The Turing Test has been the classic test of artificial intelligence for a while now. The concept is deceptively simple - to trick a human into thinking it is another human on the other end of a conversation line, not a computer - but from what I've…
auden
- 163
- 6
6
votes
2 answers
What techniques can be used to predict future attendance of students for a particular subject lecture session?
I have data of 30 students attendance for a particular subject class for a week. I have quantified the absence and presence with boolean logic 0 and 1. Also, the reason for absence are provided and I tried to generalise these reason into 3…
Ayan Paul
- 61
- 1
6
votes
1 answer
Smallest possible network to approximate the $sin$ function
The main goal is: Find the smallest possible neural network to approximate the $sin$ function.
Moreover, I want to find a qualitative reason why this network is the smallest possible network.
I have created 8000 random $x$ values with corresponding…
JavAlex
- 75
- 5
6
votes
1 answer
How can we connect artificial intelligence with cognitive psychology?
On page 62 of Artificial Intelligence and Cognitive Psychology Applications, Models (2010), Gabriella Daróczy writes
Psychology is one of the basic sciences of artificial intelligence (AI). The founder of the psychology is Wilhelm Wundt…
quintumnia
- 1,173
- 2
- 10
- 35
6
votes
1 answer
What is the difference between neural networks and other ways of curve fitting?
For simplicity, let's assume we want to solve a regression problem, where we have one independent variable and one dependent variable, which we want to predict. Let's also assume that there is a nonlinear relationship between the independent and…
Igor
- 303
- 1
- 11
6
votes
1 answer
When should we use separable convolution?
I was reading the "Deep Learning with Python" by François Chollet. He mentioned separable convolution as following
This is equivalent to separating the learning of spatial features and
the learning of channel-wise features, which makes a lot of…
Enes
- 324
- 3
- 11
6
votes
1 answer
How many nodes/hidden layers are required to solve a classification problem where the boundary is a sinusoidal function?
A single neuron is capable of forming a decision boundary between linearly seperable data. Is there any intuition as to how many, and in what configuration, would be necessary to correctly approximate a sinusoidal decision boundary?
Thanks
Ian Larson
- 61
- 1
6
votes
1 answer
What is the return-to-go in reinforcement learning?
In reinforcement learning, the return is defined as some function of the rewards. For example, you can have the discounted return, where you multiply the rewards received at later time steps by increasingly smaller numbers, so that the rewards…
nbro
- 42,615
- 12
- 119
- 217
6
votes
1 answer
Formal definition of the Object Detection problem
For many problems in computer science, there is a formal, mathematical problem defition.
Something like: Given ..., the problem is to ...
How can the Object Detection problem (i.e. detecting objects on an image) be formally defined?
Given a set of…
JavAlex
- 75
- 5
6
votes
2 answers
What is the goal of weight initialization in neural networks?
This is a simple question. I know the weights in a neural network can be initialized in many different ways like: random uniform distribution, normal distribution, and Xavier initialization. But what is the weight initialization trying to…
S2673
- 600
- 4
- 17